add-skill

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches external GitHub repositories via URLs provided by the user, where the downloaded files (such as SKILL.md) are subsequently ingested by the agent.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill imports arbitrary GitHub repositories supplied by the user at runtime via an unconstrained URL parameter, executing git clone operations from external sources as a runtime dependency.