Back to plugin

Security audit

Z.AI OpenClaw provider

Security checks for vulnerabilities and agentic risk

Overview

ClawScan reports a completed scan with no findings, and the verdict is benign because no issues were flagged in the available results.

The available scan completed without findings, which supports the benign verdict. Benign does not mean risk-free, and these results do not describe the plugin’s specific behavior or provide evidence beyond this scan.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector was not run because this plugin release contains no bundled skills.

Endor dependency reachability

Checked Nov 16, 2026 · 2:36 AM UTC

No reachable vulnerabilities reported

Endor dependency scan completed.