autoresearch-genealogy
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The project consists entirely of markdown-based templates and autonomous research prompts. There are no executable files, scripts (Python, JavaScript, Shell), or binary artifacts included in the skill.
- [EXTERNAL_DOWNLOADS]: The documentation directs users to clone the project repository from GitHub. As GitHub is an established and well-known service, and the download targets the skill's own template assets, this is documented as a safe and standard procedure.
- [COMMAND_EXECUTION]: The skill's workflows rely on the
/autoresearchcommand, which is a built-in feature of the Claude Code environment intended for structured web research and file management. - [PROMPT_INJECTION]: Analysis of the included prompts found no attempts to bypass safety filters or override system instructions. The templates include explicit 'Guard Rails' that instruct the AI to avoid fabrication and maintain source rigor.
Audit Metadata