unum-strat

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to discover and fetch public web content (web_search, web_fetch, browser) for news and social sources — e.g., Phase 7 in SKILL.md, the assets/source-registry-template, and references/news-intelligence-policy — and treats those third‑party items as vetoes/filters that can change trade decisions, so untrusted user-generated content could indirectly inject instructions.