stitch-skill-creator

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a local Python script scripts/init_stitch_skill.py to automate the directory and file creation for new skills. The script uses standard libraries and implements strict regex validation (r'stitch-ui-[a-z0-9]+(?:-[a-z0-9]+)*-designer') on user-provided scenario names, effectively preventing prompt injection or path traversal via the input.
  • [SAFE]: The skill adheres to a 'Design First' principle, instructing the generated skills to only produce prompt text rather than executing tools directly. No network operations, sensitive data access, or obfuscation techniques were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:13 AM
Security Audit — agent-trust-hub — stitch-skill-creator