ln-510-quality-coordinator

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

• Third-party content exposure detected (high risk: 0.90). The skill mandates web research and best-practice lookups (see references/evaluation_research_contract.md and the review prompts in references/agents/prompt_templates/* which explicitly instruct "Search the web" and include Stack Overflow/community sources as allowed tiers) and also launches external advisors via references/agents/agent_runner.mjs that are passed URLs/artifacts to read, so it clearly ingests untrusted public web/user-generated content as part of its workflow and uses that evidence to influence verdicts.