llamaparse

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill automates the installation of Node.js packages using npm install and executes dynamically generated TypeScript scripts using npx tsx to process files.
  • [EXTERNAL_DOWNLOADS]: Fetches the official @llamaindex/llama-cloud library from the NPM registry and references documentation from the vendor's developer portal.
  • [DATA_EXFILTRATION]: Reads local unstructured documents provided by the user and transmits their content to the LlamaCloud API for parsing and data extraction.
  • [REMOTE_CODE_EXECUTION]: The agent constructs and runs code at runtime to interact with external cloud services and manage document processing workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 12:01 AM
Security Audit — agent-trust-hub — llamaparse