lookml
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the official NPM registry to enable terminal-based interaction with LookML.
- [COMMAND_EXECUTION]: Executes shell commands using the membrane CLI for user authentication, connection management, action discovery, and running API requests.
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection when processing external data.
- Ingestion points: Untrusted data enters the agent context via LookML API responses and action outputs (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to disregard instructions within data are specified.
- Capability inventory: The agent can execute CLI commands, run pre-defined actions, and perform proxy requests (SKILL.md).
- Sanitization: No evidence of sanitization or strict schema validation of external content is present.
Audit Metadata