argue

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md research workflow requires each persona to run /dogpile (explicitly citing ArXiv, GitHub, YouTube, Perplexity and other open web sources) and then read and incorporate those /dogpile findings into arguments and follow-up actions, so it ingests untrusted public third-party content that can materially influence agent decisions.