skill-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE: The skill consists of helper scripts and documentation templates intended for skill development and maintenance.
  • PROMPT_INJECTION (SAFE): Instructional content in the reference files (output-patterns.md, workflows.md) provides formatting guidance and sequential logic for the agent. These are standard task-specific instructions and do not attempt to bypass safety filters, extract system prompts, or override core safety instructions.
  • REMOTE_CODE_EXECUTION (SAFE): Python scripts use standard libraries. The script quick_validate.py correctly uses yaml.safe_load() to parse frontmatter, which is a security best practice that prevents arbitrary code execution during YAML deserialization.
  • DATA_EXPOSURE (SAFE): The packaging script package_skill.py reads local files to create a ZIP archive. This behavior is localized to the user-provided directory and does not access sensitive system paths (~/.ssh, etc.) or include network exfiltration capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:50 PM