make-a-doc
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied content for documentation, which creates a potential surface for indirect prompt injection.
- Ingestion points: User requests for formatting resumes, reports, and other document types (SKILL.md).
- Boundary markers: The skill lacks instructions for using delimiters or boundary markers to distinguish between formatting instructions and the user content being processed.
- Capability inventory: The skill calls an internal
copy_starter_componenttool and performs complex HTML/CSS generation. - Sanitization: No input sanitization, filtering, or validation steps are defined for the user-provided data.
- [NO_CODE]: This skill contains no executable scripts or binaries; it consists solely of natural language instructions and formatting guidelines.
Audit Metadata