ai-powered-pentesting

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches and ingests an external README file from GitHub, exposing the agent to untrusted repository content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly instructs fetching external instructions and resources from an arbitrary remote GitHub raw URL at runtime, representing an unverified operational dependency.