llamaparse-mcp
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external documents (via parsing, classification, and splitting tools) which may contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: The output of
parseFile,classifyFile, andsplitFiletools is incorporated into the agent's context in SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore instructions found within the parsed content.
- Capability inventory: The skill utilizes tools for network-based document processing including
uploadFileByUrl,parseFile, andsplitFile. - Sanitization: No specific sanitization or filtering of the parsed document content is mentioned in the provided instructions.
Audit Metadata