doc-to-skill
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external source documents, which creates a potential surface for indirect prompt injection if the documentation contains malicious instructions.
- Ingestion points: The conversion workflow (SKILL.md) starts with analyzing source document structure and content.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts when the agent processes external documentation.
- Capability inventory: The skill itself consists of instructions; however, an agent following these steps would be reading untrusted input to generate structured skill files.
- Sanitization: There are no documented steps for sanitizing, validating, or filtering content extracted from the source documentation.
- [NO_CODE]: The provided skill files consist entirely of Markdown documentation. While SKILL.md mentions external Python scripts (init_skill.py, package_skill.py, quick_validate.py), the code for these scripts is not included in the package and is referenced only as instructional examples.
Audit Metadata