ClawAudit verdict
pixel-agents
openclaw-pixel-agents-dashboard
The skill installs packages, which could potentially be used for malicious purposes if not properly validated.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (6)
<script> tag in markdown — potential code injection
server/setupWizard.ts · prose · downgraded · <script>
Opens WebSocket connection
README.md · code · WebSocket
References child_process — can spawn system processes
server/hardware.ts · prose · downgraded · child_process
Uses spawn() — can execute external programs
server/index.ts · prose · downgraded · spawn(
References agent configuration files
server/config.ts · prose · downgraded · AgentConfig
Accesses sensitive environment variables
server/configLoader.ts · prose · downgraded · process.env.OPENCLAW_GATEWAY_TOKEN
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.