issue-fixer

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

• Third-party content exposure detected (high risk: 0.95). The required workflow ingests outsider-authored free text from the GitHub issue itself: it runs gh issue view <number> --json title,body,labels,comments,..., where the issue body and comments are written by non-operating users and become readable text in the agent’s context for summarization/planning.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires fetching the user-supplied GitHub issue URL at runtime (e.g., https://github.com/owner/repo/issues/123) via the gh CLI and uses the issue body to drive what changes the agent must make, so external content directly controls agent instructions and is a required runtime dependency.