Skill
ai-ml-attacks
This skill should be used when the user asks about "AI security", "ML pipeline attacks", "prompt injection", "model deserialization", "unsafe model loading",…
@allsmogView SkillSecurity
Skill
/verify-finding
Drive a single finding through CPG verification and false-positive triage.
Install
$ npx -y skills add allsmog/vuln-scout --skill verify-finding --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/verify-finding
Context preview
The summary Claude sees to decide when to auto-load this skill.
Drive a single finding through CPG verification and false-positive triage.
SKILL.md
verify-finding.SKILL.mdname: verify-finding description: Drive a single finding through CPG verification and false-positive triage.
Verify Finding
Use this task skill when the user asks to verify `VSCOUT-*`, asks whether a finding is exploitable, or asks to confirm a specific finding.
Workflow
1. Locate the finding by ID, stable key, or `file:line` in `.claude/findings.json`. 2. Run `/vuln-scout:trace` on the source-to-sink path. 3. Run `/vuln-scout:verify` for CPG-backed confirmation. 4. Call `false-positive-verifier` when controls, sanitizers, or reachability are unclear. 5. Call `local-tester` only when dynamic validation is explicitly safe and useful. 6. Run `/vuln-scout:propagate` when a confirmed pattern may repeat. 7. Update `.claude/review-ledger.json` with the final verification state.
Produces
- Updated `.claude/review-ledger.json` entry
- optional trace artifact
When NOT To Trigger
Do not trigger for broad scans, PR review, generic exploitability education, dangerous-function lists, or CPG query syntax questions that do not name a finding.
Ships withvuln-scout
AI-powered whitebox penetration testing plugin for Claude Code. 9 languages, 22 skills, 7 autonomous agents. STRIDE threat modeling, OWASP 2025 coverage, polyglot monorepo support.
Get the whole plugin
Stats
24
Stars
4
Forks
Maintained
Maintenance
Python
Language
MIT
License
3mo ago
Last commit
6mo ago
Created
Repo: allsmog/vuln-scout
Other skills on vuln-scout.
@allsmogView SkillSkill
business-logic
This skill should be used when the user asks about "business logic", "workflow vulnerability", "trust boundary", "state machine", "authorization bypass",…
@allsmogView SkillSkill
cache-poisoning
This skill should be used when the user asks about "cache poisoning", "web cache deception", "CDN cache", "proxy cache", "nginx cache", "varnish", "cache key…
@allsmogView SkillSkill
cloud-native
This skill should be used when the user asks about "cloud security", "AWS security", "GCP security", "Azure security", "Kubernetes security", "IMDS", "instance…
@allsmogView SkillSkill
compliance-mapping
This skill should be used when the user asks about "compliance mapping", "PCI-DSS", "HIPAA", "SOC 2", "NIST CSF", "regulatory requirements", "compliance…
@allsmogView SkillSkill
cpg-analysis
This skill should be used when the user asks about "Code Property Graph", "CPG analysis", "Joern queries", "CPGQL", "data flow verification", "taint tracking…
@allsmogView Skill