flowiseai
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches and installs the official Membrane CLI package (@membranehq/cli) from the public npm registry. This tool is required for the skill to authenticate and interact with the platform services.
- [INDIRECT_PROMPT_INJECTION]: The skill integrates with external FlowiseAI data, which constitutes an ingestion surface for untrusted content.
- Ingestion points: Data returned from FlowiseAI via the
membrane action runandmembrane requestcommands. - Boundary markers: No explicit delimiters are specified in the instructions for handling the external tool output.
- Capability inventory: The skill allows the agent to list/run actions and make proxied network requests to FlowiseAI endpoints.
- Sanitization: No specific sanitization or filtering logic is provided; the agent is expected to handle the resulting data according to its standard operational guidelines.
Audit Metadata