fsi-spg-earnings-preview-single

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow ingests outsider-authored free text from Kensho search results (public web/analyst/news content) into the agent context via /tmp/earnings-preview/kensho-findings.txt (Phase 4), which can include prompt-injection-like text from those sources.