update-docs
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill is constrained to managing project documentation files.
- [DATA_EXPOSURE]: The skill reads and writes to files within the 'docs/onboarding/' directory. This behavior is consistent with its primary purpose of maintaining project memory and documentation.
- [PROMPT_INJECTION]: The instructions do not contain any attempt to bypass agent safety guidelines, override system instructions, or extract system prompts.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any network operations, download external scripts, or execute shell commands. It also explicitly disables model-level invocation in the metadata.
Audit Metadata