performing-penetration-testing

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

• Third-party content exposure detected (high risk: 0.80). The skill's security_scanner.py (referenced in SKILL.md and included in scripts/security_scanner.py) explicitly fetches and parses live, user-supplied target URLs (response bodies, robots.txt, security.txt, headers, and probed endpoints), which are untrusted third‑party content that the agent reads and uses to produce findings and drive follow-up behavior.