Back to plugin

Security audit

Worktable

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marked the plugin benign, with no contextual findings reported; the scanner completed with no results, while several dimensions remain notes rather than firm assurances.

The verdict is benign, but that does not mean risk-free. Several dimensions have only note-level confidence, and the available scanner output contains no findings but little detail about the plugin’s purpose, installation, or access needs. Review those details before installing.

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 19, 2026 · 7:15 AM UTC

No reachable vulnerabilities reported

Endor dependency scan completed.