optise-helix-bluf-writer

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory workflow explicitly requires using web search/web_fetch and auto-verifying arbitrary URLs (Section 0: "Web search and web fetch ARE available" and "Auto-verify URLs via web_fetch before marking them [EXISTS]") and instructs the agent to run open-web queries (e.g., the 4-step competitor search) and to read fetched pages per the anti-hallucination rules, which means the agent will ingest untrusted public web content that can change decisions (HARD STOPs, pattern selection, BLUF contents).