sales-hunter

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

• Third-party content exposure detected (high risk: 0.70). The skill's runtime workflow (SKILL.md and references/hunter-api-reference.md) instructs the agent to call Hunter endpoints (Domain Search, Email Finder, Discover, Browser Extension/MCP) which return email records and "sources" pulled from public websites and social profiles (open third‑party content) that the agent is expected to read and use (confidence/verification influence actions like verifying, adding to campaigns), so untrusted web-origin content can materially affect decisions.