Static analysis and LLMs are a good pairing. I'm not here to argue otherwise. But a lot of teams are wiring them together in a way that quietly tur...
For further actions, you may consider blocking this person and/or reporting abuse
The cluster example is the sharpest one here: 39 fixtures hiding one real key in deploy/config.py. What would make a dismiss button show that odd one out before it lets the whole cluster go?
I’d make the button show the outliers before allowing a bulk dismissal. Things like different file paths, production configs, or secrets that don’t match the rest of the cluster should get flagged for individual review. And honestly, if even one finding looks different enough, it should be excluded from the bulk action by default. The goal is to make dismissing 39 findings easy without making the 40th disappear with them.
That default exclusion is the key part for me. A bulk button should not need a second look to catch the one file that does not belong.
Exactly. The default should be conservative, not make the reviewer responsible for spotting every outlier in a long list. If the system isn't confident a finding belongs in that cluster, leave it out of the bulk action and let someone review it separately. A few extra clicks are a much better tradeoff than silently closing a real vulnerability.
Leaving the uncertain ones out of the bulk action is the safer default.
Yeah, and it doesn't have to be complicated either. Keep the bulk action for findings that clearly meet the same criteria, and make exceptions visible instead of silently including them. I'd rather have a reviewer investigate a few extra alerts than explain later why one real secret slipped through.
The fmt-versus-tenant example is the sharpest failure mode here — the summary was correct about the wrong variable and got accepted precisely because it read well. That is why "AI as annotation, never replacement" is the load-bearing rule; a summary that can't point at the rule ID and trace is an opinion wearing a verdict's clothes. Do you track false dismissals by sampling closed findings, or is that the part teams skip because the throughput number looks too good to question?
That's exactly the problem with throughput metrics. They tell you how quickly findings disappear, not whether the decisions were correct. I'd track sampled closed findings and re-detections separately, then break false dismissals down by rule and severity. Even a small recurring review sample is better than assuming the system is accurate because it produces convincing explanations. The hardest part is making teams measure the decisions they got wrong, not just the work they processed.
Separating sampled closed findings from re-detections is the right split — a wrongly dismissed finding that comes back is the one metric throughput can't hide. The sampling question I'd push on: random for an unbiased rate, or severity-weighted so the sample spends its time where a miss hurts most? And the cultural part you name is the real blocker — a team has to be willing to publish its own miss rate before any of the measurement machinery matters.
I'd use both. Random sampling gives you a less biased picture of the overall false-dismissal rate, while severity-weighted sampling makes sure critical findings get enough scrutiny. I'd keep the results separate rather than combine them into one number. And agreed on the culture part: if teams aren't willing to make their misses visible, better measurement won't change much.
Both, kept separate, is the honest answer — one blended rate would let either sample hide behind the other. And you're right that the culture point is the ceiling: a team that won't publish its misses will just tune the sample until the numbers look good. What does publishing misses look like in practice for you — a shared dashboard, or something inside the review itself?
I'd put it in both places, but make the review record the source of truth. Each sampled finding should record the outcome, rule, severity, and reason for any incorrect dismissal. A dashboard can then show the aggregate rates and trends without hiding the individual cases. The important thing is that misses remain visible and traceable, not just reduced to a percentage.
Automating vulnerability triage with an LLM usually boils down to teams hiding an uncalibrated SAST noise floor behind non-deterministic text generation. You replace an instantaneous, zero-cost deterministic AST check with an expensive inference loop—spiking pipeline latency by 1.2s to 3.5s per finding, hogging 16–24GB of VRAM on inference nodes or burning $0.02 to $0.05 per API call—all to get an eloquent hallucination that flags a real tainted-data flow or memory corruption path as a "harmless false positive."
If you're using models in security triage, keep them advisory and strictly gated behind deterministic verification: have the model propose a minimal reproduction test or patch, spin it up in an isolated cgroup or throwaway container, and only alter ticket state if the test provably passes against the binary. When teams bypass that feedback loop and wire an LLM straight to the close button, what trade-off are they actually accepting—shaving minutes off a sprint review at the cost of your audit trail and real attack surface?
Bohdan Hordii // bohdanhordii.dev
I agree with keeping deterministic verification in the loop, especially when the model proposes a patch or reproduction test. I'd be careful about making a passing test the only route to closure, though. Some findings are resolved through configuration changes, architectural controls, or removing the vulnerable code entirely. The common requirement should be verifiable evidence tied to the exact commit, not necessarily one specific kind of test. The model can help get there, but it shouldn't own the final decision.
Two separate problems in your last replies, and they need different fixes.
A stable identity keyed on normalized location still moves. Split a file, pull a function into its own module, extract a control flow: the code relocates and the finding is the same weakness. Rule plus location turns a refactor into a new finding and orphans the old dismissal. Rule plus the artifact the check actually produced (the matched AST shape, the taint path, the fixture that fired) survives the move, and it is the thing a second reviewer can rerun. That is what makes evidence at closure checkable instead of merely mandatory. "Validated upstream" is prose; a check, its artifact, and the commit are a record.
You are also right that a passing test cannot be the only exit, because a config change and deleted code have no test. The common requirement is an artifact that ties the closure to that commit, whatever produced it.
Whether a claimed fix actually happened is the work I do. If you want the longer version aimed at Cyclopt's pipeline instead of the general argument, it is $25, agree first, no link until you say yes. The thread already has the substance; the paid part is the working design.
That's a fair distinction, especially the point about identity surviving refactors. Keying findings to the actual evidence artifact rather than the file location is a much stronger approach. Otherwise, you lose continuity exactly when the code changes.
And I agree that the closure mechanism needs to support different kinds of fixes. A deleted code path, a config change, and a patched vulnerability won't all produce the same kind of test result. The important thing is that each closure has reproducible evidence tied to the commit. That's the part I'd want to get right before automating any of it.
You have answered both of my comments and half this thread, and not once have you said what Cyclopt records when something closes. So one question, no theory: pick a finding you closed last month and tell me what exists for it today. A comment on the ticket means the record is the explanation, and every rule in this thread passes it. A rerun of the check at that commit means you already have the thing I am describing, and this is only about reading it back.
Fair question. I should separate what I'm arguing for from what I can actually claim Cyclopt records today. I don't want to invent an example or pretend I've inspected a closure record that I haven't. The concrete test is simple: can we take a finding closed last month, recover the original scanner evidence, identify the commit it was assessed against, and reproduce the verification? If not, that's exactly the gap this discussion is about.
The important boundary is between triage and disposition. AI can cluster evidence, propose severity, and draft a remediation plan, but closure should require an explicit control: a reproducer or compensating-control check, an accountable owner, and evidence that the condition is no longer exploitable. Otherwise the summary becomes a very polished way to hide uncertainty.
I like that distinction between triage and disposition. That's really where the boundary should be. The AI can help prioritize and explain, but someone or something still needs to establish that the underlying risk is gone. I'd also make the evidence requirement depend on the type of resolution, since a patch, a compensating control, and removed code won't all have the same verification path.
The triage/disposition split is the right operational boundary. A close gate should require a linked remediation artifact—merged diff, configuration change, or accepted risk with expiry—so an AI summary can accelerate investigation without becoming closure evidence.
The field your gate is missing is the re-open path. An accepted risk with an expiry date is a promise the calendar keeps only if something reads the date: a scheduled job that reopens the finding when it passes, tied to the same evidence record. Without it, expiry becomes the quietest way to close a finding twice.
A receipt from outside security tooling: macOS keeps two trust stores, the system keychain and the flat cert.pem that curl and git actually read. After a CA is blocked, "revoked" and "still trusted" are both true until an OS build replaces the file. A control that expires and a store that never re-reads it are the same failure with better paperwork.
That’s a good point. An expiry date only matters if there’s an actual mechanism behind it. I’d treat accepted risk as a time-bound state, not a permanent closure: the finding should automatically reopen when the deadline passes, with the original evidence and owner still attached. Otherwise the record says the risk was temporary, but the system has no way to enforce that.
The date needs a reader with a name. Who reads it on a Sunday, and what happens to their queue when the deadline lands while they are away? If the honest answer is nobody, the expiry is a note to the next auditor, not a control.
The fmt example suggests a cheap mechanical check: make every proposed close name the variable and line from the scanner's own trace, and reject it when the explanation argues about something that is not on that trace. Here the summary reasoned about tenant while the rule fired on fmt in the ORDER BY. It will not catch every mistaken verdict, but it catches the case where the reasoning is about a different variable than the finding. Does your pipeline keep the trace in a form an explanation could be checked against like that?
That's a good check. The wrong-variable case is exactly the kind of mistake we should be able to catch without relying on the reviewer to spot it. If the explanation can't point back to the actual sink and trace that triggered the rule, it shouldn't be allowed to recommend closure. It won't prove the finding is valid, but at least it stops the AI from confidently answering a different question.
Exactly, it doesn't prove the finding, it just stops the summary from answering a different question. That alone would have saved the case in your post.
Right. It’s a small guardrail, but a useful one. Before debating whether a finding is a false positive, make sure the explanation is actually addressing the finding the scanner reported. That should be the minimum bar, not the final verification.
The distinction between volume and false-dismissal rate is useful. Do you keep a sample of closed findings tied to the rule ID and commit so reviewers can reconstruct the original evidence after the code changes?
That's exactly the kind of traceability I'd want. A sampled closure should retain the rule ID, original scanner trace, and commit it was assessed against, so a reviewer can reconstruct what was actually evaluated even after the code changes. I wouldn't want to claim every system already preserves that history, but it's a good standard to measure against.
Yes, and I would put it on every close rather than on a sample. A sample is a second system: an export job, a retention window, someone who remembers to refresh it. Rule ID, scanner trace and commit on the dismissal record itself, and then the sample is a query instead of a pipeline.
The reason belongs in the same place. If it can't be shown from the finding's own data, it isn't a reason yet.
The part I'd want to hear about is what the record is keyed to. A trace that names line 412 does not survive the next commit. What did you end up storing, the raw scanner output or something normalized?
The line that hit me: "An explanation is a hypothesis about a finding. It is not evidence that the finding is resolved."
I felt this deeply, just from the technical writing side. I recently had an article rejected by an editor because it read too much like an AI summary.
My original draft perfectly explained what the Python code did and summarized the steps. It looked clean, just like those 12 tidy cards in your example. But the editor pointed out that it lacked the actual "evidence" of a human developer: the bugs, the struggle, and the "why" behind the code. I had summarized the syntax but stripped out the engineering reality.
I had to delete the whole thing and rewrite it, adding the concrete proof of my own troubleshooting.
"Plausible" is not the same as "Correct." Whether we're talking about a security scanner dismissing a vulnerability or a writer summarizing a codebase, the raw evidence has to survive the summary. Brilliant breakdown.
That's a great parallel. You can have a technically accurate summary and still lose the most important part: the reasoning and evidence behind it. The bugs, the decisions, and the things that didn't work are what make engineering writing credible. Glad you brought that perspective into this discussion.
Based on my experience and recent development, an elegant AI explanation is not a security fix.
To prevent fluent hallucinations from closing real vulnerabilities, we must enforce a strict "Deterministic Exit" framework across its automated security lifecycle, locking down how findings are triaged and archived:
Mechanical Symbol & Sink Verification: An automated triage helper applies an input-matching rule. If the assistant's written analysis fails to explicitly reference and reason about the exact vulnerable Sink and token trace flagged by the scanner (e.g., arguing about a clean variable while missing the tainted parameter next to it), the system rejects the recommendation, forcing manual human oversight.
AST-Based Artifact Identity: To stop refactoring from creating "identity drift" and orphaning old baseline records, keys vulnerabilities to the unique abstract syntax tree (AST) shape and data-flow trace rather than mutable line numbers. If code moves to a different module, the tracking context survives the refactor, preserving the continuity of the original decision.
The Re-Detection Alert Loop: measure security by verified accuracy, not by uncalibrated throughput. A system that logs and surfaces High-Attention Re-Detections if an active scanner fires on a code path previously dismissed on an assistant's note. This provides engineering leads with a true, sampled signal to audit and measure our false dismissal rate.
This is a strong framework, especially the idea of treating closure as a deterministic state transition rather than a language-model decision. I'd add one nuance around AST-based identity: syntax shape and data-flow context are much more useful than line numbers alone, but they still need to be tied to the actual check artifact and commit. Refactors can change the structure too.
The common thread across all four points is that every closure needs evidence someone else can reproduce and challenge. AI can make triage faster, but it should never get to define what counts as proof.
I think that one possible evolution or at least the one that I used in one of my open source project that can be checked by the following :
The fmt example is the whole problem in one snippet. The summary was right about a variable the rule never fired on. One check I'd add: make the AI explanation name the exact sink and trace hop it's reasoning about, and reject any "likely false positive" that doesn't reference the same line the rule flagged. That catches the wrong-variable case mechanically instead of hoping a reviewer notices.
On false dismissals, the cheapest signal I've found is re-detections. If the same rule fires in the same function after a refactor and the earlier finding was closed on an AI note, that's a dismissal you go back and grade. It's not a full accuracy rate, but it's free and it points straight at the bad closes.
Re-detections are the right free signal, and they grade the code more often than they grade the close. The same rule firing in the same function after a refactor can mean the earlier close was wrong, or that the sink moved out from under a check that was fine. Without the check that closed it and the commit it ran at, you cannot tell those apart, so the re-detection points at a bad close without convicting it. The commit is what turns go-back-and-grade into a query: diff from there, rerun the recorded check, and it either still passes (the close was wrong) or fails on code that changed (the close was right and the code moved).
Whether the signal is countable at all depends on how the scanner keys a finding. If it keys on rule plus function instead of line number, a rename keeps the key and you can count it. If it keys on line, every refactor mints new findings and the old ones are gone, so the free signal only ever counts the closes that did not matter.
Does yours survive a function rename?
That's a really important distinction. A re-detection is a signal, not a verdict. Without knowing what check ran and what commit it ran against, you can't tell whether the original dismissal was wrong or the code simply changed later. On the function rename question, I'd favor a stable finding identity based on the rule and normalized code location or data-flow context, rather than line numbers alone. Refactors shouldn't erase the history of a finding.
I like the re-detection idea. It's a practical signal teams can start tracking without building a whole accuracy framework first. And requiring the explanation to reference the exact sink and line makes sense too. I'd still keep re-detections as something to investigate rather than automatically count as false dismissals, since the code may have changed in between.
This highlights an important distinction between AI-assisted analysis and actual security verification. AI can make vulnerability reports easier to understand, but closing a finding should always depend on reproducible evidence, not just a convincing explanation. At IT Path Solutions, we see AI integration and software reliability as areas where accuracy, traceability, and human oversight are essential. Preserving scanner traces, linking fixes to specific commits, and tracking false dismissals can make AI-assisted security workflows much more dependable.
Agreed. Traceability is what makes the distinction practical. Keeping the original scanner evidence, linking the fix to a commit, and checking false dismissals gives teams a way to verify whether the workflow is actually improving decisions.
"Resolved: input is validated upstream" with no link is the scariest sentence in this post. I'd make one rule: the AI can group and explain, but it can't close a finding without pointing to a line of code or a commit. Otherwise it's just a very polite way of saying "trust me, bro".
Exactly. A line or commit is a good starting point, but the important part is that the evidence actually supports the resolution. “Validated upstream” should point to something a reviewer can inspect, not just sound plausible.
Alert volume is easy to instrument. False dismissals aren't, unless every close carries the check that closed it.
Three fields on the dismissal record: which check ran, what artifact it ran against, which commit. Then the false-dismissal rate is a query instead of a sampling project. Rerun the recorded checks against current artifacts, count the ones that come back red. A close with only an explanation attached is not a pass, it's an unverified close. Count it separately or it sits in the denominator pretending to be a decision.
Your cluster case has the same shape. Similarity ranks the 39+1, it does not check them. Two findings looking alike does not mean both are fixtures, and the one live key is not distinguishable by how similar it looks. Only a check per member separates them, so what the record has to hold is the check, not the neighbor.
Adjacent receipt from this week. Apple published a block on eight compromised eMudhra intermediate CAs. Two write-ups then disagreed about whether /usr/bin/curl on macOS still trusted them, both with sources. Reading the block notice settles nothing, because macOS carries two trust stores: the keychain, and a flat bundle shipped inside the OS image that curl and other file-based tools read. "Revoked" was the claim. Which store the process consults was the state, and only opening that file tells you which one you have.
That is failure mode 3 with an extra layer: name the artifact the runtime actually consults, not the one the summary cites.
The distinction between a check and an explanation is a good one. I especially like the idea of treating unverified closes as a separate category, because otherwise the metrics can look healthy while the actual risk stays hidden. And the artifact point matters too. Even if a check passed, you need to know exactly what it ran against and which commit it covered. Otherwise, the record gives you confidence without giving you a way to reproduce the decision.
hordii_bohdan has the cost right and the substitution wrong. The triage loop does not replace an AST check. It replaces a person reading the same finding, and the pipeline pays for that reading anyway, only later and without a record.
My point is the exit. Whatever proposed the close, model or person, the close names the check that ran, the artifact it ran against, and the commit. madhabcoder's list is the one I would enforce: rule ID, file and line, link to the fix. gautamtalksdev's test is the cheapest of all: reject a close that argues about a symbol the scanner never fired on.
None of that is inference. It is three required fields at the moment a finding becomes invisible.
I like that framing: the exit is where the accountability needs to live. It doesn't really matter whether the AI or a human proposed the dismissal if the system can't show what actually justified it. And that symbol check is a great practical safeguard. If the explanation doesn't address what triggered the finding, it shouldn't even be eligible for closure. Simple rule, but it could prevent a lot of bad dismissals.
This one hit home. 'Resolved: input is validated upstream' with no link isn't a record, it's a vibe. I'd let the AI group and explain findings all day, but closing one should still need the original rule ID, the file and line, and a link to the actual fix or validation. Otherwise six months later you're doing archaeology on your own repo.
Exactly. The link is what makes the decision useful six months later. "Validated upstream" sounds reasonable until someone has to find where that validation actually happens. I'd make the evidence mandatory at closure, not an optional field people fill in when they remember. The AI can write the explanation, but the record needs something another reviewer can independently verify.
The distinction between an AI explanation and a verified resolution is especially important in security workflows. I'd also preserve the exact commit or code snapshot used during triage; otherwise, even a well-documented human decision can become difficult to reproduce after the code changes. One additional safeguard is to track false dismissals by rule category and severity, not just as an overall rate. That can expose cases where the assistant performs well on noisy findings but consistently misses a particular class of vulnerability. AI can reduce review effort, but the evidence and closure decision need to remain independently verifiable.
Absolutely. Looking at the overall false-dismissal rate can hide some pretty serious problems. An assistant might do well with noisy low-severity alerts but struggle with injection or authentication issues. Breaking the numbers down by rule category and severity would make those weaknesses much harder to miss. The commit snapshot is equally important because a decision is only useful if you can reproduce what was actually reviewed.
A summary can help triage, but closure should require evidence that the vulnerable path changed and that the fix was independently verified. Attaching the failing reproduction, patched diff, test result, and deployment version makes the finding auditable instead of turning a fluent explanation into a status change.
Yes, that chain makes a closure auditable. The failing reproduction shows what was broken, the diff shows what changed, and the test result shows whether the fix works. The deployment version matters too, otherwise you may verify a patch that never reached the environment in question.
Great article! This is equally relevant to AI-assisted test automation. As we explore LLM-as-a-Judge and self-healing tests, preserving evidence and measuring false dismissals are critical. AI should support decisions, not silently make them.
Thanks, Rimon! I think the same principle applies to test automation. A self-healing test can be useful, but if it changes or dismisses a failure without preserving what failed and why, you lose the evidence needed to trust the result. LLM-as-a-Judge should help assess the evidence, not quietly become the final authority.
I've found that keeping the original finding separate from the AI summary saves a lot of pain later. The summary helps you move faster, but when something breaks, you still need the exact trace and commit.
Same here. The summary is useful during triage, but when someone needs to revisit the decision, the original trace and commit are what make it possible to understand and verify what happened.
The failure-mode framing is spot on — the fix is to treat the AI summary as an attachment, not the record. Keep the rule ID, file, line and data-flow trace as immutable metadata and let the assistant only annotate severity and deduplication on top; anything it flags as noise should lower priority, never auto-close without the original evidence. I see the same trap in desktop app error attribution: clustering crash logs by LLM summary sounds great until the raw stack traces that would confirm the root cause are the first thing dropped.
That stack-trace comparison is a good parallel. Once the raw evidence is discarded, you can't reliably challenge the summary or reconstruct why the system made its decision. AI annotations should add context without replacing the source finding.