docs-seeker
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external websites and GitHub repositories, creating a surface for indirect prompt injection.\n
- Ingestion points: Documentation content fetched via
WebFetch(Phase 2) and repository data processed byRepomixinto XML format (Phase 3).\n - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands when processing retrieved content.\n
- Capability inventory: The agent can execute system commands (
git clone,npm,repomix) and perform network requests.\n - Sanitization: No explicit sanitization or filtering of external data is mentioned.\n- [COMMAND_EXECUTION]: The skill uses
Bashto install therepomixutility, clone repositories, and generate repository summaries. These commands are necessary for the skill's core functionality of analyzing codebase documentation.\n- [EXTERNAL_DOWNLOADS]: The skill fetches content from external documentation URLs and GitHub repositories. It also installs therepomixtool from the NPM registry. These sources are generally well-known and expected for this type of technical task.
Audit Metadata