general-counsel-advisor

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it handles external data.
  • Ingestion points: Data enters the system via the --input JSON files processed by scripts/legal_risk_register.py, scripts/contract_portfolio_analyzer.py, and scripts/regulatory_calendar_generator.py.
  • Boundary markers: There are no explicit delimiters or 'ignore' instructions wrapping the external data in the resulting markdown output.
  • Capability inventory: The associated scripts are restricted to data parsing and report generation; they lack network access, file writing capabilities outside of output, or subprocess execution.
  • Sanitization: The scripts incorporate JSON field values directly into markdown without escaping or validation against instructional patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 08:25 PM
Security Audit — agent-trust-hub — general-counsel-advisor