skills/etalab-ia/skills/rag-parse/Gen Agent Trust Hub

rag-parse

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to generate and run shell commands using the lit CLI tool to parse documents, perform batch conversions, and generate page screenshots.
  • [EXTERNAL_DOWNLOADS]: Recommends the global installation of the @llamaindex/liteparse package via npm, along with system dependencies like LibreOffice and ImageMagick using standard package managers (Homebrew or apt).
  • [PROMPT_INJECTION]: As the skill processes untrusted document content, it presents an indirect prompt injection surface.
  • Ingestion points: Processes external files including PDFs, Word documents, and spreadsheets provided by the user.
  • Boundary markers: The instructions do not define delimiters or explicit 'ignore instructions' warnings for the parsed content.
  • Capability inventory: The agent can execute CLI commands, write files to disk, and potentially connect to a user-defined OCR server.
  • Sanitization: No automated validation or escaping of the extracted document text is specified before it is consumed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 12:22 PM