legal
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external legal documents and web content, which constitutes an ingestion surface for untrusted data.
- Ingestion points: Processing web content and external data for GDPR audits and TOS generation (SKILL.md).
- Boundary markers: Includes instructions to treat external data as hostile and use explicit MCP loops (sequentialthinking) for risk assessment.
- Capability inventory: Mentions tool execution via an ExecutionProxy interface and saving to a MemoryStore interface (SKILL.md).
- Sanitization: Explicitly mandates redacting secrets and PII before sharing context with subagents.
Audit Metadata