optise-helix-prompt-pack-builder

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory operating rules and workflow explicitly instruct the agent to perform web searches and fetch public pages (e.g., "Web search and web fetch ARE available" in Section 0, "Verify competitor relationships via the 4-step search protocol" and "Auto-verify URLs via web_fetch before marking them [EXISTS]" in Section 0 and Section 4), meaning it ingests untrusted third‑party web content and uses those findings to drive decisions and next actions.