academic-search

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through its document analysis features.
  • Ingestion points: Untrusted data enters the agent context when users share academic papers or abstracts for analysis, utilizing the extract_text_from_pdf tool defined in the MCP server configuration.
  • Boundary markers: The skill definition lacks specific delimiters or system instructions designed to prevent the model from executing commands that might be hidden within the text of an academic paper.
  • Capability inventory: The skill includes tools for file reading (extract_text_from_pdf) and file generation (create_docx).
  • Sanitization: There is no evidence of text sanitization or verification of external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:20 AM