chinese-legal-renewal-watcher
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists of instructional text and contains no scripts, binaries, or external code dependencies.
- [PROMPT_INJECTION]: The skill ingests untrusted data from local contract trackers and documents, creating a surface for indirect prompt injection.
- Ingestion points: Files located in
managed-agent-cookbooks/renewal-watcher/and user-provided tables. - Boundary markers: No explicit delimiters for external content are specified.
- Capability inventory: File system read and write operations.
- Sanitization: No explicit sanitization of ingested content is performed, though a lawyer-review disclaimer is present.
Audit Metadata