skill-manager

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists exclusively of markdown documentation and YAML frontmatter. There are no executable scripts (Python, JavaScript, or Bash) included in the skill package.
  • [COMMAND_EXECUTION]: The documentation includes examples of shell commands such as grep, wc, head, and git tag. These are explicitly presented as manual steps for a user to perform file validation and version control within their own environment. There is no automated execution of these commands by the agent.
  • [DATA_EXPOSURE]: Analysis of the markdown content and YAML metadata revealed no hardcoded credentials, API keys, or attempts to access sensitive system paths (e.g., SSH keys or cloud provider configurations).
  • [EXTERNAL_DOWNLOADS]: No remote URLs, external script fetches, or third-party package installations were detected. The skill operates entirely on local markdown files.
  • [PROMPT_INJECTION]: The instructions focus on structural management and standardization. No patterns related to bypassing safety filters or overriding system instructions were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 01:24 PM