tabular-review-lawvable

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes content from untrusted external documents (PDF and DOCX), creating an attack surface for indirect prompt injection where content within the files could attempt to override the sub-agent's instructions during data extraction.
  • Ingestion points: File content is ingested through the pdf and docx skills as specified in the sub-agent prompt template in SKILL.md.
  • Boundary markers: The template does not utilize strict delimiters or clear instructions for the agent to ignore commands found within document content.
  • Capability inventory: The skill utilizes filesystem discovery (Glob), background agent execution (Task), and spreadsheet creation (xlsx).
  • Sanitization: There is no evidence of sanitization or validation of document content before it is processed by the agent or written to the Excel output.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 10:17 AM