security-reviewer

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's workflow tells the agent to load the penetration-testing guidance (references/penetration-testing.md, referenced from SKILL.md for "active testing, reconnaissance"), which explicitly includes commands that fetch public web data (e.g., curl to crt.sh, subfinder/amass, aws s3 ls --no-sign-request, sqlmap against arbitrary URLs), so the agent would ingest and act on untrusted third-party content that can influence subsequent actions.