skill-goal-extractor

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

• Third-party content exposure detected (low risk: 0.10). The required workflow directs the agent to read packaging documentation from a GitHub repository, which is a public repository containing outsider-contributed text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs installation of an external third-party repository from GitHub, representing a common unofficial operational dependency with medium severity.