What problem does it solve?
Security teams and penetration testers waste significant time manually verifying low-quality, false positive vulnerability findings from automated scanners and AI agents. This skill acts as an adversarial pre-filter to triage findings before hands-on testing, eliminating wasted effort on non-issues.
Core Features & Use Cases
- Evidence Quality Assessment: Evaluates each finding for specificity, evidence chain completeness, and reproducibility to gauge how much trust to place in the report.
- False Positive Pattern Matching: Auto-rejects known low-value findings like missing security headers without exploitation scenarios or self-XSS that only affects the attacker's own session.
- Severity Calibration: Re-ranks findings based on actual demonstrated impact rather than agent claims, so teams prioritize real, high-risk vulnerabilities first.
- Use Case: A red team running a web application pentest can feed all scanner and agent output into this skill to get a prioritized list of only high-confidence findings to test, skipping obvious false positives.
Quick Start
Use the vuln-critic skill to triage and prioritize all findings from your latest web application penetration test.