msa-review-saas
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No evidence of malicious intent or harmful code was found in the instructions, examples, or reference materials. The skill logic is entirely centered on legal document processing.
- [SAFE]: The skill does not hardcode credentials, access sensitive file paths (e.g., .ssh or .env), or perform network operations to untrusted domains.
- [SAFE]: While the skill ingests untrusted legal documents, the risk of indirect prompt injection is mitigated by the AI being directed to follow a highly structured workflow with predefined analysis tiers and a specific output schema.
- [SAFE]: The metadata and instructional content are consistent with the stated purpose of providing legal tech automation. No obfuscation or persistence mechanisms were detected.
Audit Metadata