apollo

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow uses ClawLink to connect to Apollo and then perform actions like searching/enriching/creating CRM records; those actions necessarily fetch and ingest Apollo-side free-text fields (e.g., contact/company/deal descriptions, names, notes) into the agent’s LLM context, which is outsider-authored content from a third-party service.

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 causes npm to fetch and execute the @useclawlink/cli package from the npm registry (see https://www.npmjs.com/package/@useclawlink/cli), so remote code is fetched/executed at runtime and controls the agent's connect/auth/actions.