insightsoftware
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill relies on the author's official CLI tool (
@membranehq/cli) and infrastructure (getmembrane.com) to manage the integration, which is consistent with its intended functionality. - [SAFE]: The skill implements secure credential management by leveraging the Membrane platform's OAuth/connection flow, ensuring that sensitive API keys are not exposed to the agent or stored locally.
- [SAFE]: The skill provides a surface for data ingestion from Insightsoftware reports and records. While this is standard for such integrations, it constitutes an indirect prompt injection surface where external data could potentially contain malicious instructions.
- Ingestion points:
membrane action run,membrane requestinSKILL.md. - Boundary markers: Absent.
- Capability inventory: Network requests via the Membrane CLI proxy.
- Sanitization: Not specified; relies on platform-level handling and agent constraints.
Audit Metadata