openclaw-expert

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.95). Suspicious: the URL points to a direct install.sh on an unverified domain (openclaw.ai) and the curl | bash pattern is a high-risk delivery mechanism for arbitrary malware unless you verify the source, inspect the script, and confirm signatures/checksums.

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

• Third-party content exposure detected (high risk: 0.90). The skill's required automation and integration workflows explicitly instruct the agent to fetch and act on public third‑party content (e.g., "Check GitHub for new PRs", "Check competitor pricing pages", "Research trending topics" in references/automation.md, and web_search/ngrok/ElevenLabs setup in references/deployment.md and references/integrations.md), so untrusted/user-generated web content is read and can materially influence actions.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill explicitly instructs system-level deployment actions—systemd service setup, UFW/firewall configuration, curl|bash install, and Docker host privileges—which entail modifying system files and changing machine state that require elevated privileges.