email-finder-hunter

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 Hunter API endpoints (e.g., /v2/domain-search, /v2/people/find, /v2/discover) which return email addresses, profiles and "sources" scraped from public websites and social profiles — untrusted third‑party content the agent is expected to read and act on.