document-parser
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external documents (PDF, Word, etc.) using the agentbody_document_parse tool, creating a surface for indirect prompt injection where instructions embedded in documents might influence agent behavior.
- Ingestion points: External file content parsed by agentbody_document_parse as described in SKILL.md.
- Boundary markers: Absent. There are no specific delimiters or instructions to help the agent distinguish between its core instructions and the data extracted from documents.
- Capability inventory: The skill facilitates tool execution via the sandbase_call_tool gateway.
- Sanitization: Absent. The skill does not specify any sanitization, filtering, or validation of the content extracted from external documents.
Audit Metadata