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.
