Skills
skills/greyhaven-ai/claude-code-config/grey-haven-skill-creator/Gen Agent Trust Hub

grey-haven-skill-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill includes a local script scripts/init_skill.py that the agent executes to automate project setup.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill has an attack surface where user-provided inputs are used as script arguments. 1. Ingestion points: sys.argv in scripts/init_skill.py triggered by instructions in SKILL.md. 2. Boundary markers: Absent in the execution instructions. 3. Capability inventory: The script can create directories and write files to the filesystem using the Bash tool. 4. Sanitization: The script uses pathlib.Path.resolve() for basic path handling but does not implement strict validation on the skill_name input.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:36 PM