typesense
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clipackage from the official NPM registry. This utility is the vendor's primary tool for managing integrations. - [COMMAND_EXECUTION]: Several commands are provided for the
membraneCLI to perform authentication (membrane login), connection management (membrane connect), and action execution (membrane action run). These are standard operations for the platform's intended use case. - [PROMPT_INJECTION]: The skill utilizes a pattern where natural language intents are passed to the CLI to discover or create actions, which represents an indirect prompt injection surface.
- Ingestion points: The
intentparameter inmembrane action listandmembrane action create(SKILL.md). - Boundary markers: None explicitly defined in the provided instruction templates.
- Capability inventory: Execution of arbitrary connector actions via
membrane action run(SKILL.md). - Sanitization: Validation and intent parsing are handled by the Membrane platform's backend infrastructure.
Audit Metadata