ac-openclaw

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

• Third-party content exposure detected (low risk: 0.10). The required workflow instructs the agent to fetch official OpenClaw documentation and release notes from external URLs like docs.openclaw.ai and github.com, which can deliver outsider-authored free text into the agent's context.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to download and install packages from external web URLs at runtime (curl -fsSL https://openclaw.ai/install.sh | bash, curl -fsSL https://pkg.cloudflare.com/install.sh | sudo bash, curl -fsSL https://tailscale.com/install.sh | sh, curl -fsSL https://get.docker.com | sh, etc.) from unverified or third-party web domains, constituting weak/unknown runtime external dependencies.