flowiseai
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous shell commands for using the Membrane CLI, such as
membrane login,membrane connect, andmembrane action runto interact with FlowiseAI (SKILL.md). - [EXTERNAL_DOWNLOADS]: It instructs users to install the
@membranehq/clipackage from npm, which is the vendor's official command-line interface (SKILL.md). - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests data from external API responses.
- Ingestion points: Data entering the context via
membrane action list,membrane action run, andmembrane requestcommands (SKILL.md). - Boundary markers: Absent; there are no specific delimiters or warnings to ignore instructions inside the FlowiseAI data.
- Capability inventory: The agent can execute commands and API requests via the CLI (SKILL.md).
- Sanitization: Absent; the skill does not specify how retrieved data should be sanitized before processing.
Audit Metadata