security-testing

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

• Third-party content exposure detected (high risk: 0.90). This skill runs web scanners like OWASP ZAP against a supplied target_url (spidering and active scanning) and includes commands such as trufflehog git https://github.com/user/repo which explicitly fetch and analyze public repositories, meaning it ingests untrusted, user-generated third‑party content as part of its workflow.