nimble-web-expert

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests live content from arbitrary public URLs and social/social-network agents (see SKILL.md commands like nimble extract, nimble search, nimble map, nimble crawl and the agent table in references/nimble-agents/SKILL.md), and that untrusted third‑party content is parsed and used to decide follow-up actions (browser-actions, network-capture, parser schemas) as part of the core workflow, enabling indirect prompt-injection risk.