satuit

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the official Membrane CLI tool (@membranehq/cli) from the public NPM registry. This is a vendor-owned package required for the skill's operations.
  • [COMMAND_EXECUTION]: Orchestrates various CRM tasks by executing membrane CLI commands. These commands are used for session management (login), resource discovery (search, action list), and data operations (action run, request).
  • [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection as it ingests and processes data from the external Satuit CRM API.
  • Ingestion points: API responses from actions and proxy requests within SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external data as untrusted.
  • Capability inventory: The skill possesses the ability to execute CLI commands and make network requests through the vendor proxy.
  • Sanitization: The skill relies on the agent's ability to handle structured JSON data returned by the CLI.
  • [DATA_EXFILTRATION]: No exfiltration risks detected. Network operations are routed through the vendor's infrastructure which manages authentication headers and connection lifecycle securely.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 04:40 PM