ai-make-skill

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a strictly limited set of shell commands (git rev-parse, test, wc) for environment detection and file validation, which are explicitly restricted in the YAML frontmatter.
  • [DATA_EXPOSURE]: The skill contains proactive safety instructions to prevent the leakage of environment variables, specifically noting that the environment should not be printed to protect user credentials.
  • [INDIRECT_PROMPT_INJECTION]: While the skill generates content based on user input, it includes several mitigation strategies: a detailed procedural workflow, a mandatory verification step (Step 5) to ensure output integrity, and an 'Edit Scope' section that restricts file operations to the current working directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 02:43 PM