skill-system-creator

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines automated operations to execute included Python scripts (scripts/init_skill.py and scripts/package_skill.py) for managing the skill development process.
  • [SAFE]: The skill incorporates security best practices, such as using yaml.safe_load() for parsing configuration and strictly validating user-provided skill names against a safe regex pattern (^[a-z0-9-]+$).
  • [PROMPT_INJECTION]: The skill manages potential indirect injection surfaces (skill metadata) through the following controls:
  • Ingestion points: User-provided skill names and descriptions.
  • Boundary markers: Standard YAML frontmatter delimiters (---).
  • Capability inventory: Filesystem read/write and subprocess execution (proc.exec) limited to the skill's own scripts.
  • Sanitization: Enforced regex validation for names and length constraints for descriptions in quick_validate.py.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 11:19 PM