postmark

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow uses ClawLink to connect to Postmark and then execute “postmark_*” actions; these actions necessarily ingest Postmark-derived free-form text (e.g., email content, bounce details, template/message text, webhook payloads) into the agent’s LLM context via the CLI’s tool outputs, which are authored by an external party (Postmark system data and/or end recipients), creating an indirect prompt-injection surface.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running "npx @useclawlink/cli" which fetches and executes remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli) at runtime and is required for the agent to operate, so it directly executes external code.