market-audit

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches arbitrary public webpages using "python3 scripts/analyze_page.py " and passes the resulting analyze_page JSON to parallel subagents that must quote evidence and base scores/actions on that page content, thereby exposing the agent to untrusted third-party content from the provided URL.