hunt
CommandTest for a specific vulnerability class against target endpoints using curated payloads.
Generate a markdown penetration test report.
$ npx -y skills add frendysanusi/claude-pentest-skills --agent claude-code
Generate a markdown penetration test report.
/report --finding F-001 Generate report for a single finding /report --full Generate complete engagement report /report (no args) Same as --full
Load `skills/report.md` — Report templates and writing guidelines.
No agent persona is activated for reporting — use neutral, professional tone.
Read all engagement state files:
1. Load the specific finding from `findings.md` 2. Generate using the Per-Finding Template from `skills/report.md` 3. Calculate CVSS 3.1 score using the scoring guide 4. Include CWE and WSTG references 5. Output the finding report in markdown
1. Collect all VALIDATED findings, sorted by severity (Critical → Low) 2. Generate using the Full Report Template from `skills/report.md` 3. Populate all sections:
4. Output the complete report in markdown
Display the report in the conversation. Offer to save:
Report generated. Would you like me to save it to: engagements/<target>/report-<date>.md
Before outputting, verify:
AI-powered web application penetration testing skills with Claude Code
Test for a specific vulnerability class against target endpoints using curated payloads.
Define and authorize the target scope for a penetration testing engagement. This is the **mandatory first step** — all other…
Display the engagement progress dashboard. Read-only — does not modify any state files.
Run the 6-gate strict quality gate on unvalidated findings.
Audit a file, directory, or whole repo for insecure default configuration: fallback secrets, default credentials, fail-open…
Check text against AGT prompt-injection, context-poisoning, and MCP threat detectors.
Show which external bug-bounty tools are installed on this machine and print install hints for the missing ones. Curated from…