github-repo-architect

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and inspect external GitHub repositories (e.g., "gh repo list", "gh search repos", "gh repo clone", and Read("packages/…/package.json") in the Usage Examples and Cross-Repository Synchronization sections), which ingests untrusted, user-generated third-party content that can influence subsequent actions like edits, commits, and PR creation.