sales-account-intelligence

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required workflow explicitly instructs using runtime “search” and “extract” from external sources (e.g., official websites, credible news, job postings, customer stories), which would ingest outsider-authored free text into the agent’s LLM context via the search/extraction results.