Security audit
Anthropic Vertex
Security checks for vulnerabilities and agentic risk
Overview
ClawScan rates the anthropic-vertex plugin benign with high confidence; the completed scan reported no findings, and all five security dimensions are marked ok.
The completed scan supports a benign verdict, but benign does not mean risk-free. Consider whether this plugin suits your needs and review the permissions requested during installation.
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 · 2:33 AM UTC
1 reachable vulnerability
- Medium
undici vulnerable to Denial of Service via unhandled exception in cache-interceptor response replay
CVE-2026-120222Direct dependency of@openclaw/anthropic-vertex-provider@2026.11.4
