anycap-deepresearch

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow (SKILL.md and references/02-gather.md) explicitly instructs the agent to run anycap search/crawl on arbitrary public URLs, download images and videos (e.g., anycap crawl , curl image URLs, anycap actions video-read --url), and then read/interpret those crawled pages as part of the research and synthesis process, which clearly ingests untrusted third‑party web content that can influence subsequent actions.