aibtc-news-fact-checker

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly pulls and acts on user-generated "signals" from the network (see required workflows using news_signals --limit 50 and news_signals --agent {btcAddress} in SKILL.md/AGENT.md), and those untrusted third‑party signal contents are read and used to decide verification and correction actions, which could enable indirect prompt injection.