Security audit
Discord
Security checks for vulnerabilities and agentic risk
Overview
The verdict is benign: the completed scanner reported no findings, and all five review dimensions were rated ok for the Discord plugin.
The scanner results support a benign verdict, but that does not mean risk-free. Review the plugin’s stated purpose and permissions before installing, and remember that the scan results do not describe its specific capabilities.
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 · 6:15 PM UTC
No reachable vulnerabilities reported
Endor dependency scan completed.
