judgment-document-generation
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are purely logical and focused on legal document generation. No evidence of obfuscation, credential harvesting, or unauthorized network access was found.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted case fact descriptions as its primary input. While this represents a data ingestion surface, the impact is negligible as the skill lacks access to sensitive system tools or network operations.
- Ingestion points: S1 input ('案件事实描述').
- Boundary markers: None identified.
- Capability inventory: Legal analysis, reasoning, and document generation (Atomic capabilities AS4, AS5, AS6, AS8, AS9, AS16, AS49, AS50).
- Sanitization: None identified.
Audit Metadata