Back to plugin

Security audit

Worktable

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign, and the completed MCP scan reported no specific findings; the evidence is limited, so this does not mean the plugin is risk-free.

The verdict is benign, but the scan results offer limited evidence about the plugin’s purpose, installation, and environment access. Review the plugin’s description and requested access before installing, and consider whether they fit your needs.

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 16, 2026 · 9:26 PM UTC

No reachable vulnerabilities reported

Endor dependency scan completed.