webiny

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill retrieves data from Webiny CMS (e.g., content entries, form submissions), which serves as an ingestion point for untrusted external content. This creates a surface for indirect prompt injection where data could potentially influence agent actions.
  • Ingestion points: Output from membrane action run and membrane request commands in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters to separate external data from agent instructions.
  • Capability inventory: The agent has access to the membrane CLI for executing actions and making network requests.
  • Sanitization: No explicit content validation or escaping of the fetched data is described.
  • [EXTERNAL_DOWNLOADS]: The integration instructions include the installation of the @membranehq/cli package via npm. This is an expected utility from the vendor for managing connections and actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 08:30 AM