public-repo-explorer

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md workflow explicitly instructs the agent to perform a shallow git clone of an arbitrary public repository URL and to read files like README.md and source code from the cloned repo (steps "Perform a Shallow Clone" and "Examine Requested Content"), which are untrusted, user-generated third-party contents that the agent will interpret and act on.