clawddocs

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to use WebFetch to fetch and read public documentation from https://docs.openclaw.ai/ (e.g., https://docs.openclaw.ai/llms.txt and https://docs.openclaw.ai/) as part of its required workflow, exposing it to untrusted third‑party web content that could contain instructions influencing the agent's actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs using WebFetch at runtime to retrieve documentation from https://docs.openclaw.ai/ (notably https://docs.openclaw.ai/llms.txt and https://docs.openclaw.ai/), and that fetched content would be injected into the agent's responses/decision flow, so it directly controls prompts and is a required runtime dependency.