proworkflow
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes the vendor's official CLI (@membranehq/cli) for managing ProWorkflow interactions.
- [SAFE]: All API authentication is performed via the 'membrane' platform, which manages credential lifecycles and provides secure proxying to the ProWorkflow service, eliminating the risk of credential exposure.
- [PROMPT_INJECTION]: The skill interacts with ProWorkflow data (Messages, Tasks), creating a surface for indirect prompt injection. This is a low-risk surface common to data-processing skills. Ingestion points: ProWorkflow API (SKILL.md). Boundary markers: Absent. Capability inventory: 'membrane action run' and 'membrane request' (SKILL.md). Sanitization: None.
Audit Metadata