lemlist

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow uses ClawLink to call Lemlist actions at runtime (e.g., npx @useclawlink/cli describe/run lemlist ...), which will ingest Lemlist-returned free-form text (campaign/lead/message/task content) authored by Lemlist users/your org’s contacts rather than the operating user, creating an indirect prompt-injection surface via the tool’s LLM-readable outputs.

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" (see https://www.npmjs.com/package/@useclawlink/cli), which fetches and executes remote code from the npm registry at runtime and is required for the skill to operate.