legal-red-team
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted legal documents, presenting a surface for indirect prompt injection attacks.
- Ingestion points: Document text processed by scripts/legal_fact_checker.py and scripts/legal_quality_scorer.py via the --input or --text arguments.
- Boundary markers: None identified in the script logic or markdown instructions.
- Capability inventory: File read operations in scripts/legal_fact_checker.py and scripts/legal_quality_scorer.py; no network or shell execution capabilities.
- Sanitization: Content is processed via regex without specific sanitization of instruction-like patterns.
- [SAFE]: The provided Python scripts are self-contained, use only standard library modules, and perform no suspicious activities such as credential harvesting, network communication, or persistence modification. All external references are to official legal databases for verification purposes.
Audit Metadata