brave-search

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls the Brave Search API via the OneKey Gateway (see SKILL.md and scripts/brave_web_search.py / scripts/brave_local_search.py), returning public web/local search results from arbitrary third‑party sites which the agent is expected to read and could materially influence subsequent actions.