skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation describes the use of local utility scripts (scripts/init_skill.py and scripts/package_skill.py) for initializing and validating skill directories. These references are part of a standard development workflow and do not involve untrusted remote sources.\n- [PROMPT_INJECTION]: The skill outlines a methodology for gathering user requirements to create new specialized agents. While this process involves processing untrusted user data, the documentation itself does not contain malicious triggers or safety bypass attempts.\n
  • Ingestion points: User-provided examples and requirements gathered during the understanding phase (Step 1).\n
  • Boundary markers: No specific boundary markers or 'ignore' instructions are mandated in the provided templates.\n
  • Capability inventory: The guide describes the creation and execution of scripts (Python/Bash) and the maintenance of reference files.\n
  • Sanitization: No explicit sanitization or validation of user-provided strings is detailed before inclusion in the generated skill files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 03:24 PM