skill-best-practices

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to guide the creation of other agent skills. It contains standard procedural instructions and templates.
  • [COMMAND_EXECUTION]: The skill utilizes a local Python script (scripts/validate-metadata.py) to validate skill metadata. Technical review of the script confirms it is safe, performing only string validation using standard libraries (argparse, re, sys) without network access or sensitive file operations.
  • [DATA_EXFILTRATION]: No network operations, credential harvesting, or sensitive data access patterns were identified in any of the skill files.
  • [PROMPT_INJECTION]: No instructions attempting to bypass safety filters or override agent behavior were found in the core logic or templates.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 03:45 AM