uberduck
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the
@membranehq/clipackage from the official npm registry. This is a vendor-owned tool used to interface with the Membrane platform. - [COMMAND_EXECUTION]: Runs
membraneCLI commands to perform authentication, service connection, and action execution. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from Uberduck, which enters the agent's context as untrusted input.
- Ingestion points: Data returned from
membrane action runcalls. - Boundary markers: None explicitly defined in the skill instructions.
- Capability inventory: Action discovery, creation, and execution via the
membraneCLI. - Sanitization: Not specified in the instructions; relies on the agent's internal processing.
Audit Metadata