cognitive-doc-design

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes two commands intended for documentation review workflows. These utilize standard local tools (git and gh) to list changed markdown files and view pull request statistics (additions, deletions, file count). Both commands are benign and directly support the skill's stated purpose of optimizing documentation and review efficiency.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to help write or edit documentation (READMEs, PR descriptions). While the agent may interact with user-provided documentation content, the skill does not perform any execution, network operations, or sensitive file access based on that content, maintaining a safe operating environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 05:25 PM
Security Audit — agent-trust-hub — cognitive-doc-design