research-project-orienter
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates by reading local project metadata files (YAML and Markdown) located in a specific
.research/directory. It uses these files to generate a summary for the user without executing any code or accessing sensitive system files. - [SAFE]: The skill explicitly instructs the agent to avoid scanning the entire repository and to refrain from reading data files or PDFs unless specifically requested by the user, which follows the principle of least privilege.
- [SAFE]: No remote code execution, external downloads, or data exfiltration patterns were detected. The skill uses standard instructional language to guide the AI's summarizing behavior.
Audit Metadata