github-search

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

• Third-party content exposure detected (high risk: 0.90). This skill directly fetches and ingests user-generated public GitHub content via the gh CLI—e.g., readme_analyzer.fetch_repo_readme (reads README via gh api), repo_search.fetch_file_content (fetches file contents), code_search.* (runs gh search code/symbol/path), and repo_search.search_issues—then parses and uses that content to drive classification, code analysis, and subsequent actions, so untrusted third-party content can materially influence the agent.