cowork-deal-room

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted documents (PDFs, .docx, .xlsx, .csv) from a user-provided directory, creating a surface for indirect prompt injection attacks.
  • Ingestion points: Untrusted data enters the agent context in Phase 1 (Inventory) and Phase 2 (Legal Analysis) via the Read tool as described in references/phase-procedures.md.
  • Boundary markers: The instructions lack explicit boundary markers or instructions to the LLM to ignore embedded commands within the analyzed documents.
  • Capability inventory: The skill utilizes powerful tools including Bash, Write, and WebSearch, which could be abused if an attacker-controlled document successfully influences agent behavior.
  • Sanitization: There is no evidence of content sanitization or validation of the text extracted from documents before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:25 AM
Security Audit — agent-trust-hub — cowork-deal-room