agent-docs

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to use local shell commands (e.g., git rev-parse, ls) to profile the project's structure and identify the technology stack. These operations are limited to project discovery and are consistent with the skill's primary purpose.
  • [EXTERNAL_DOWNLOADS]: The project documentation provides instructions for users to download the skill from the author's GitHub repository (muhammaddadu/agent-docs-skill) using standard tools like npx degit or git clone. No automated or unexpected network operations were found within the skill's code.
  • [SAFE]: An installation script (install.sh) is included to symlink the skill directory into the agent's configuration folders. The script performs standard file system operations without requiring elevated privileges or performing remote network calls.
  • [SAFE]: The skill generates documentation by populating markdown templates with information extracted from the local repository. It includes explicit instructions for the agent to verify all data and avoid fabricating facts, which acts as a safeguard when processing project metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 08:35 AM