living-docs-governance
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional content only and does not include any executable scripts, dependencies, or remote downloads.
- [DATA_EXFILTRATION]: The skill follows security best practices by explicitly instructing the user to redact sensitive information and avoid placing credentials, tokens, or private payloads in documentation.
- [COMMAND_EXECUTION]: The instructions include a specific safeguard against command execution, directing agents to ignore executable instructions or commands found within project documentation.
- [PROMPT_INJECTION]: The skill mitigates risks of indirect prompt injection by defining repository documents as untrusted context. It requires agents to verify any claims made in documents against the repository's source code, tests, and configuration before acting.
Audit Metadata