vuln-critic

Filter low-quality and false positive vulnerability findings from scanners and agent output.

11|1|Updated May 4, 2026
One-click install
npx skills add https://github.com/dreadnode/capabilities --skill vuln-critic
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: vuln-critic
Source: https://github.com/dreadnode/capabilities/tree/main/capabilities/web-security/skills/vuln-critic
Command: npx skills add https://github.com/dreadnode/capabilities --skill vuln-critic

SYSTEM DOCUMENTATION & REQUIREMENTS

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.

Frequently Asked Questions about vuln-critic

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I filter false positive vulnerability findings from automated scanner output?

Filter false positive vulnerability findings by applying evidence quality assessment and pattern matching to scanner output, eliminating wasted testing time on known low-value issues like missing security headers or self-XSS before manual verification.

What is vulnerability triage and how does it improve penetration testing workflows?

Vulnerability triage is the process of pre-filtering automated scanner findings to assess evidence quality, match false positive patterns, and re-rank severity based on actual impact, ensuring red teaming efforts focus only on high-confidence findings.

How do I calibrate vulnerability severity based on actual demonstrated impact?

Calibrate vulnerability severity by re-ranking findings based on actual demonstrated impact rather than agent claims, evaluating each finding for specificity, evidence chain completeness, and reproducibility to prioritize real high-risk vulnerabilities first.

Can I use this skill to triage web application pentest findings from AI agents?

Yes, you can use this skill to triage web application pentest findings from AI agents by feeding all scanner and agent output into it to get a prioritized list of only high-confidence findings for exploit verification.

What are common false positive patterns in web security scanner reports?

Common false positive patterns in web security scanner reports include missing security headers without exploitation scenarios and self-XSS that only affects the attacker's own session, which are auto-rejected during evidence-based vulnerability triage.