Security audit
GitHub Copilot agent runtime
Security checks for vulnerabilities and agentic risk
Overview
ClawScan marked the plugin benign with high confidence; the completed scan reported no findings, so it identified no issues in the areas assessed.
The available scan completed and reported no findings, supporting the benign verdict. That does not guarantee the plugin is risk-free; consider whether it meets your needs and review what access it requests when 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 was not run because this plugin release contains no bundled skills.
Endor dependency reachability
Checked Nov 17, 2026 · 10:30 AM UTC
No reachable vulnerabilities reported
Endor dependency scan completed.
