gorgias

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). At runtime the skill uses ClawLink to connect to the Gorgias app and then “find/describe/run” actions, which implies the agent will ingest Gorgias-provided free-form text (e.g., ticket/customer messages or action results) into the LLM context; this is outsider-authored content from a third-party service.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime setup uses "npx @useclawlink/cli", which fetches and executes remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli) as a required dependency and thus runs external code that can control agent actions.