written-consent

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized network operations were detected. The skill operates within a restricted local file environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external precedents and local repository files.\n
  • Ingestion points: Local configuration and precedent files located in ~/.claude/plugins/config/claude-for-legal/corporate-legal/ and user-uploaded documents.\n
  • Boundary markers: Absent; the instructions do not define explicit delimiters to separate template content from drafting instructions.\n
  • Capability inventory: Limited to text generation, precedent searching, and writing to specific local project directories. The skill does not have access to network tools or arbitrary code execution capabilities.\n
  • Sanitization: No explicit validation or escaping of ingested legal text is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:58 PM
Security Audit — agent-trust-hub — written-consent