instantly

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow invokes a ClawLink CLI to call Instantly APIs and ingest returned data (e.g., campaign/lead lists, analytics, emails) into the agent’s LLM context; this is outsider-authored free text/data originating from the Instantly service rather than the operating user’s own tenant prompts/files.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to run npx @useclawlink/cli which fetches and executes remote code from the npm package (see https://www.npmjs.com/package/@useclawlink/cli) at runtime, and that CLI then controls actions/prompts against the Instantly/ClawLink service, so this is a runtime external dependency that executes remote code.