documentation-writer
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands against the local checkout to verify their validity and output for documentation purposes. This behavior is the primary intended function of the skill and is accompanied by safety constraints.
- [SAFE]: The instructions explicitly mandate the use of clearly fake placeholders (e.g., "sk-or-v1-...") for any commands requiring authentication or credentials, preventing the accidental use or exposure of real secrets.
- [SAFE]: No malicious behaviors such as unauthorized data exfiltration, obfuscation, or remote code downloads were detected in the skill's instructions or templates.
Audit Metadata