pp-mailchimp

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to call Mailchimp API endpoints (e.g., digest, compare, segments audit, reporting get-surveys-id-responses, landing-pages, file-manager) to fetch user-generated campaign/landing-page/survey/file content and to read/interpret those results as part of workflows (e.g., send-checked, compare, digest), so untrusted third-party content from Mailchimp accounts can materially influence agent actions and enable indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires installing the CLI via an npx command that fetches and runs remote package code (npx -y @mvanhorn/printing-press install mailchimp --cli-only, i.e. from the npm package @mvanhorn/printing-press at https://www.npmjs.com/package/@mvanhorn/printing-press), which is a runtime external dependency that executes remote code.