power-automate
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the user to install the
@membranehq/clipackage globally via npm to interact with the Membrane platform. This is the official tool provided by the vendor for this integration.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Power Automate actions, which could contain malicious instructions. Mandatory evidence chain: 1. Ingestion points: Output frommembrane action runandmembrane request(SKILL.md). 2. Boundary markers: None provided. 3. Capability inventory:membrane action run,membrane action list, andmembrane request(SKILL.md). 4. Sanitization: None specified in the instructions.
Audit Metadata