elintp
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied technical topics to generate documentation, which represents a surface for potential instruction injection.
- Ingestion points: User input provided via the
/elintp <topic>command, mapped to the$ARGUMENTSvariable inSKILL.md. - Boundary markers: The instructions include a 'Red Line' section that forbids specific types of descriptive text and a 'Writing Guidelines' section to constrain the content structure.
- Capability inventory: The skill is authorized to perform local file-write operations to create HTML documents in the current directory or a
docs/subfolder. - Sanitization: The skill relies on a 'Delivery Self-Check' phase to review and filter the content before the file is finalized.
Audit Metadata