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/cli package 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 from membrane action run and membrane request (SKILL.md). 2. Boundary markers: None provided. 3. Capability inventory: membrane action run, membrane action list, and membrane request (SKILL.md). 4. Sanitization: None specified in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 02:19 AM