Security audit
Code Agent
Security checks for vulnerabilities and agentic risk
Overview
This coding automation plugin clearly discloses its powerful access and provides controls for plans, repository changes, and updates.
Install only where chat users may legitimately run developer commands. Use trusted repositories, review setup scripts and hooks, and prefer explicit plan and merge approvals. Configure backend sandboxing separately and keep unrelated secrets out of the Gateway environment. Project content may reach the selected AI provider and remain in local transcripts. This assessment includes static runtime inspection, not live execution testing.
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Endor dependency reachability
Checked Nov 16, 2026 · 9:12 AM UTC
No reachable vulnerabilities reported
Endor dependency scan completed.
