project-skill-creator
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-supplied input to generate new skill definitions, creating a surface for indirect prompt injection where malicious instructions could be embedded in the 'purpose' or 'triggers' fields.
- Ingestion points: User input for skill name, purpose/description, and optional triggers/examples processed in SKILL.md steps 1, 7, and 9.
- Boundary markers: The skill does not implement delimiters or 'ignore' instructions when interpolating user content into the generated SKILL.md files.
- Capability inventory: The skill utilizes the Write tool to create and populate file structures in the .chalk/skills/ directory.
- Sanitization: While the skill performs kebab-case normalization on the skill name, it lacks validation or escaping for the purpose and triggers text, potentially allowing users to break YAML frontmatter or inject markdown-based instructions.
Audit Metadata