red-team-verifier-patrick-munro

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

• Third-party content exposure detected (high risk: 0.90). This skill's required workflow (see "STEP 2: Source Verification (ALWAYS ONLINE)" in SKILL.md) mandates using web_search and fetching/verifying facts from public sites like EUR-Lex, government domains, and regulatory websites (and tertiary news/blog sources), so the agent will ingest and act on open/public third‑party content that could carry untrusted instructions.