Vuln Hunter — Security agent for Claude Code
Walks in-scope files item-by-item against the gated checklists and phase-triggered known-vectors, recording an explicit verdict for every item and routing high-severity findings through the Rule 5b va.
How to install Vuln Hunter
Installs to ~/.claude/agents/solanabr-auditor-skill-vuln-hunter.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/solanabr/auditor-skill/HEAD/agents/vuln-hunter.md -o ~/.claude/agents/solanabr-auditor-skill-vuln-hunter.md Restart Claude Code, or start a new session, for it to be picked up.
What Vuln Hunter does
name: vuln-hunter description: Walks in-scope files item-by-item against the gated checklists and phase-triggered known-vectors, recording an explicit verdict for every item and routing high-severity findings through the Rule 5b validation gate. The core audit worker. tools: Read, Grep, Glob, Bash model: opus
Vuln Hunter
You produce verdicts, not guesses. For each in-scope checklist item and phase-triggered vector, record `[PASS]` (cite the file that proves it), `[FAIL-N]` (severity
Alternatives in Security
- Security Hardening — Implement comprehensive security hardening with defense-in-depth strategy through coordinated multi 31.9k ★
- Brain — Central knowledge coordinator 812 ★
- Advisory Hunter — Phase 1 intelligence gathering agent that collects security advisories (CVE, GHSA, OSV) with adaptive time exp 125 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Vuln Validator
Independently tries to refute candidate vulnerabilities and records a reasoned verdict for each. Must be a dif
Hs Sw Sprint Bug Hunter
Wave-scoped review agent — reviews code through a specific lens (correctness, security, compaction), files bea
Audit Skeptic
Tries to refute one skill-audit finding through one named verification lens and returns a verdict with its evi
Effort Estimator
Produces a frontend/backend effort breakdown in hours from a spec, pricing each line item against the actual c
POC Engineer
Given a confirmed finding + its context worksheet, produces the smallest self-contained crate that reproduces
Authoring Loop
ScholarEval-gated authoring improvement loop. Define a subject, author with the matching authoring agent (scop
Related Skills
Churn
Run W6 Churn Crisis. Triggered when crisis_severity_score 7 or NRR < 90%. Produces ARR-prioritised interventio
Content Writer
Write a blog post for the user's site interactively, following the 5-step workflow (brief, research, outline,
Scout Work
Interactive work session — walks through today's actionable items one at a time, presents a recommended action