api-radar

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md shows it fetches and reads content from public GitHub repositories (e.g., using "gh pr view", "gh pr diff", and "gh api repos/{owner}/{repo}/contents/{file_path}" in the PR/Commit/Branch Search and Step 1 workflows), which are untrusted, user-generated third‑party sources that the agent is expected to interpret and that can materially influence its analysis and next actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly calls the GitHub API at runtime (e.g. "gh api repos/{owner}/{repo}/contents/{file_path}?ref={branch_name}" and decodes the returned file content), which fetches raw repository files that are then injected into the agent's analysis/context and therefore can directly control prompts; this external content is a required runtime dependency.