skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides detailed documentation and structural templates for developing AI agent skills.
  • Core instructions focus on modular design, conciseness, and progressive disclosure for context management.
  • Defines a clear directory structure for scripts and references in 'references/anatomy.json'.
  • [COMMAND_EXECUTION]: Includes a Python script snippet in 'references/skill-validation-guide.md' for automating the verification of skill metadata.
  • The script utilizes 'yaml.safe_load' for parsing frontmatter, which is a security best practice that prevents arbitrary code execution during YAML deserialization.
  • The logic is limited to checking file existence and validating naming conventions using regular expressions.
  • [PROMPT_INJECTION]: The skill describes instructions for the agent to follow when assisting a user, which are task-specific and do not include patterns typical of jailbreaks or safety filter bypasses.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 08:23 AM
Security Audit — agent-trust-hub — skill-creator