startup-coach
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a shell script (
link-readmes.sh) to automate the creation of symlinks (CLAUDE.md,AGENTS.md) to the project'sREADME.md. This is a standard workspace configuration task and the script performs safe local filesystem operations. - [INDIRECT_PROMPT_INJECTION]: The skill includes a workspace review feature that reads the project's
README.mdand directory structure to provide auditing and recommendations. - Ingestion points: The skill ingests data from the workspace root
README.mdand directory tree. - Boundary markers: Audit logic relies on structural analysis of the
README.mdfile rather than specific injection delimiters. - Capability inventory: The agent can generate markdown documentation from templates and execute the provided workspace setup script.
- Sanitization: The skill audits project metadata for completeness but does not implement specific sanitization for external workspace content.
Audit Metadata