document
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill serves as a processing layer for untrusted external documents which may contain malicious instructions intended to manipulate the agent context.
- Ingestion points: Binary and text documents processed via
document::to-markdownanddocument::ocr. - Boundary markers: No specific delimiters or instructions to ignore embedded content are described in the conversion output.
- Capability inventory: Includes text extraction, image/asset extraction, and vision-based OCR.
- Sanitization: The conversion process to markdown format acts as a structural sanitization layer by stripping active binary content.
Audit Metadata