sitespeakai

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package from the public npm registry. This is the official command-line tool for the Membrane platform and is expected for this skill's functionality.
  • [PROMPT_INJECTION]: The skill's ingestion of data from SiteSpeakAI creates a surface for indirect prompt injection, where content from external chatbots or organizations could influence the agent's context.
  • Ingestion points: Commands such as membrane action list, membrane action run, and membrane request retrieve data from SiteSpeakAI.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external data as untrusted.
  • Capability inventory: The skill utilizes shell command execution via the membrane CLI and requires network access to function.
  • Sanitization: The instructions do not define specific validation or escaping mechanisms for the data returned from the API.
  • [SAFE]: The skill demonstrates positive security posture by explicitly instructing users to let the platform handle authentication and avoids the use of hardcoded secrets or API keys.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 07:44 PM