New - Extreme Noise Reduction for Secrets and CVEs 🚀
8 Jul 2026
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.
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.
Last updated
Was this helpful?