flexport-enterprise-rbac
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data including workload inventories and credential registries to design RBAC policies. 1. Ingestion points: Workload-to-outcome inventory and credential registry referenced in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Read, Grep, Write, and Edit tools are utilized for discovery and artifact creation. 4. Sanitization: No explicit validation is performed on ingested data, though redacted receipts are required for output. This surface could allow maliciously crafted input to influence policy design.
- [EXTERNAL_DOWNLOADS]: The skill references official Flexport domains including api.flexport.com and developers.flexport.com. These references target well-known service resources required for the governance workflow.
Audit Metadata