Back to plugin

Security audit

Artil

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates the plugin artil benign, with no findings from the completed AIG-MCP scan; confidence is medium, so the result is reassuring but not a guarantee of safety.

The verdict is benign, and the completed scan reported no findings, but confidence is medium and the results provide limited detail about the plugin. Review the plugin’s description and requested access before installing, and install only if they match what you need.

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 findings are pending for this release.

Endor dependency reachability

Checked Nov 13, 2026 · 10:47 AM UTC

No reachable vulnerabilities reported

Endor dependency scan completed.