skill-creator
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by allowing user-provided content to be incorporated into generated AI agent instructions (skills), which could be manipulated to include harmful logic.
- Ingestion points: User requests to create or document new agent patterns as specified in the SKILL.md description.
- Boundary markers: The template provided in assets/SKILL-TEMPLATE.md does not include delimiters or specific instructions to isolate user-provided content from the skill's structural instructions.
- Capability inventory: The skill uses Write and Edit tools to create new files in the skills directory, and defines common shell command patterns in the template.
- Sanitization: There are no established procedures for sanitizing or validating the user-provided requirements before they are written into the new skill instructions.
Audit Metadata