openclaw-customizer

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly tells the agent to fetch live public OpenClaw documentation URLs (e.g., the https://docs.openclaw.ai/* links listed in SKILL.md) and to load/interpret external docs as part of its workflow for proposing config and actions, so third‑party web content can materially influence behavior.