cmd-docs-idiot-proof

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for documentation management and does not exhibit any malicious behaviors or security vulnerabilities.
  • [PROMPT_INJECTION]: Instructions are focused on stylistic guidelines for documentation (e.g., reordering sections, using specific Markdown elements) and do not attempt to bypass safety filters or override agent behavior.
  • [COMMAND_EXECUTION]: While the skill defines strict rules for formatting command blocks within documentation, it does not instruct the agent to execute those commands or perform arbitrary shell operations.
  • [DATA_EXFILTRATION]: There are no network operations, URL references, or attempts to access sensitive system files or credentials.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes documentation files as input. Although it lacks explicit boundary markers for untrusted content, the risk is mitigated by a mandatory 'Approval Gate' which forces the agent to show a change preview and wait for explicit user approval before modifying any files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 10:15 AM
Security Audit — agent-trust-hub — cmd-docs-idiot-proof