prospect-360-b2b

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly requires the WebSearch tool (Step 2a) and optional Superpowers browser automation and then instructs the agent to fetch and ingest untrusted public content from sites like Instagram, LinkedIn, Google Reviews, YouTube, Twitter/X and arbitrary webpages in the Research Process rounds, and to use those findings to generate messages, call scripts, and action plans—so third‑party content can directly influence the agent's decisions and actions.