openclaw-customizer

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly tells the agent to fetch live documentation from public URLs (e.g. https://docs.openclaw.ai/*), and it references web fetch/search tooling and ClawHub community skills (public community content), so the agent will read and interpret open/public third‑party content as part of its workflow, exposing it to indirect prompt injection.