assess-docs
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's logic is entirely confined to local documentation analysis and reporting. Its behavior aligns with its documented purpose.
- [COMMAND_EXECUTION]: File system activity is restricted to reading markdown files within the 'docs' directory and writing a summary report to 'docs/calibration/doc-assessment.md'. No unauthorized shell command execution was detected.
- [DATA_EXFILTRATION]: There are no network requests or external communication protocols (like curl or fetch) defined in the instructions. Data remains within the local environment.
- [REMOTE_CODE_EXECUTION]: The skill does not include any mechanisms for downloading external scripts or installing unverified packages.
- [PROMPT_INJECTION]: While the skill processes external data (markdown files), which is an inherent surface for indirect prompt injection, it contains no patterns designed to bypass safety filters or override the agent's core instructions.
Audit Metadata