skill-creator-doctor

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): The script scripts/add_user_verification.py is designed to automatically inject a 'MANDATORY USER VERIFICATION REQUIREMENT' section into SKILL.md files. This section uses high-authority directives such as 'CRITICAL', 'MANDATORY', and 'DO NOT' to constrain agent behavior. While intended as a safety guardrail, these patterns resemble prompt injection techniques used to override system instructions.
  • Data Exposure (LOW): The script scripts/add_user_verification.py contains a hardcoded absolute path (/home/noam/my-projects/...) which exposes the author's local directory structure and username ('noam').
  • Safe Practices (SAFE): The script scripts/quick_validate.py correctly uses yaml.safe_load() when parsing YAML frontmatter, preventing potential YAML deserialization vulnerabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:07 PM