uithub-fetcher

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests content from public GitHub repositories, issues, and pull requests via the uithub CLI as described in SKILL.md (e.g., "uithub owner/repo" and issue/PR fetch examples), which are user-generated/untrusted web sources that the agent is expected to read and use to drive analysis and follow-up actions, creating a clear avenue for indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill invokes the uithub CLI at runtime to fetch arbitrary GitHub repositories (e.g., https://github.com/facebook/react) and uses the fetched repository files as agent input, meaning remote repo content can directly control the agent's prompts/context.