remarkety
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Installs the official Membrane CLI tool (@membranehq/cli) from the npm registry. This is a standard utility provided by the vendor to facilitate platform interactions.
- [COMMAND_EXECUTION]: Executes membrane CLI commands to manage authentication, discover actions, and perform API operations. These are routine administrative tasks within the supported ecosystem.
- [DATA_EXFILTRATION]: Utilizes a proxy request command (membrane request) to communicate with the Remarkety API. This mechanism allows the skill to perform HTTP operations through the platform's infrastructure, which manages authentication headers and session refresh automatically.
- [PROMPT_INJECTION]: Indirect prompt injection surface detected.
- Ingestion points: Data returned from the Remarkety API via 'membrane action run' and 'membrane request' commands.
- Boundary markers: None identified in the skill instructions.
- Capability inventory: Command execution via 'membrane' CLI for action runs and API requests.
- Sanitization: None identified; relies on platform-level proxying and model guardrails.
Audit Metadata