switchboard

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the membrane command-line interface to interact with the Switchboard API, including connection management and action execution. These operations are standard for the tool's intended use.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the npm registry. This is a vendor-provided tool used for the skill's primary function.
  • [PROMPT_INJECTION]: The skill features a surface for indirect prompt injection because it ingests data from external Switchboard actions (ingestion point: membrane action run output). While the instructions do not specify boundary markers or sanitization for this data, the available capabilities are restricted to vendor-managed CLI functions.
  • [SAFE]: No malicious patterns, such as obfuscation, persistence, or unauthorized data exfiltration, were detected. The skill follows secure authentication patterns and utilizes a trusted vendor CLI.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 09:12 PM
Security Audit — agent-trust-hub — switchboard