brave-search

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

• Third-party content exposure detected (high risk: 0.90). This skill performs live web searches via the Brave Search API (https://api.search.brave.com/res/v1/search) as documented in SKILL.md and the scripts (scripts/search.sh, search_ja.sh, search_news.sh), ingesting untrusted public web results (titles/URLs/descriptions) that the agent reads and could materially influence subsequent actions.