> For the complete documentation index, see [llms.txt](https://help.aikido.dev/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.aikido.dev/changelog/q3-2026/new-extreme-noise-reduction-for-secrets-and-cves.md).

# New - Extreme Noise Reduction for Secrets and CVEs 🚀

Aikido’s secrets detection and dependency engine now have LLM agents that use reasoning to identify truly exploitable issues.

* **Secrets AutoTriage** helps determine whether a detected value is likely a real credential and whether it creates actionable risk.
* **CVE Exploitability Analysis** determines whether a CVE is likely exploitable in your codebase and how urgently it should be addressed. From there, it can act on its own: upgrading, downgrading, snoozing, or ignoring findings automatically based on rules you control.\
  \
  Each run is logged, so you can see what was analyzed and what actions the agent took.

<figure><img src="/files/8qdN9iIOF8EcOViRU0EP" alt=""><figcaption></figcaption></figure>

**Why it matters**

* **Verification on top of detection**: LLM agents assess open-source dependency CVEs and leaked secrets against your codebase to see what is actually exploitable.
* **Smarter prioritization**: findings can be escalated *or* deprioritized based on real-world risk (e.g., live/high-scope secrets, practically exploitable reachable CVEs).
* **Short rationale included**: each outcome includes an explanation so teams can review and override when needed.

**How these fits into Aikido**

* **Secrets AutoTriage**: runs after entropy detection, determining whether a discovered secret is a real, exposed value and the riskiness. Most findings are handled by defined rules, but in ambiguous cases the surrounding code is used to determine what the credential is for, its liveness, and scope.
* **CVE Exploitability Analysis**: adds LLM reasoning based on how your code uses the package, then it can upgrade, deprioritize, or snooze/ignore the CVE automatically based on the codebase-aware findings.

→ [Read more about Secrets AutoTriage](https://help.aikido.dev/ai-and-dev-tools/secrets-autotriage)

→ [Read more about CVE Exploitability Analysis](https://help.aikido.dev/ai-and-dev-tools/cve-exploitability-analysis)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://help.aikido.dev/changelog/q3-2026/new-extreme-noise-reduction-for-secrets-and-cves.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.