Back to plugin

Security audit

Run Observer

Security checks for vulnerabilities and agentic risk

Overview

Prompt-injection indicators were detected in the submitted artifacts (system-prompt-override); human review is required before treating this skill as clean.

Before installing, make sure you want all recent OpenClaw run content logged locally. Keep the viewer URL/token private, keep the gateway on loopback, rotate the token if shared, and be aware that the viewer may make external icon requests. ClawScan detected prompt-injection indicators (system-prompt-override), so this skill requires review even though the model response was benign.

Static analysis

No suspicious patterns detected.