cs-guide
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local script located at
.codestable/tools/search-yaml.pyto search through documentation metadata. This is a project-specific tool used for internal administrative tasks. - [DATA_EXPOSURE]: The skill is designed to read from and write to the
docs/directory and.codestable/configuration folder. This behavior is restricted to the local project environment and aligns with its primary purpose of documentation management. - [PROMPT_INJECTION]: As the skill processes existing documentation and design files (untrusted data) to generate new content, it has an indirect prompt injection surface. However, the impact is minimal because the skill only writes Markdown files to defined documentation paths and does not perform sensitive operations like network requests or system-level configuration changes.
Audit Metadata