am-literature-rag

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The scripts/amrag.py script uses the subprocess module to call the pdftotext binary (part of the Poppler suite) for extracting text from PDF files. The implementation follows security best practices by passing arguments as a list rather than a shell string, preventing shell injection attacks.
  • [EXTERNAL_DOWNLOADS]: When using the 'dense' or 'hybrid' backends, the skill downloads the all-mpnet-base-v2 embedding model from Hugging Face using the sentence-transformers library. This is a standard operation for local embedding generation and uses a well-known service.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data (user-provided PDFs). While this introduces a surface for indirect prompt injection—where malicious instructions hidden in a paper could attempt to influence the agent—the skill includes specific instructions to the agent to ground all answers strictly in the retrieved citations and to explicitly label general knowledge.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 06:02 AM