sentry

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

• Third-party content exposure detected (high risk: 0.75). The required workflow uses ClawLink to connect to Sentry and then the agent runs actions like “fetch alerts/issues/monitors” which cause the LLM to ingest Sentry’s retrieved text (outsider-authored content from a third-party service) into its context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires running "npx @useclawlink/cli" which fetches and executes remote npm package code at runtime (see https://www.npmjs.com/package/@useclawlink/cli), so external code is executed and relied upon for the skill to function.