nimble-agents

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly uses nimble_web_search with deep_search=true to "fetch and extract full page content" during the required Discovery and generate/update background workflows (see SKILL.md Step 1D and generate-update-and-publish.md), so it ingests untrusted public web pages and uses that content to drive agent generation and next actions.