Security audit
Ward Codex Doctor
Security checks for vulnerabilities and agentic risk
Overview
This skill gives bounded instructions for analyzing local Codex telemetry, with local-only defaults and explicit user control for AI-based diagnosis.
Before installing, understand that this skill is intended to inspect local Codex session telemetry and may generate local JSON/HTML reports. Use telemetry-only mode unless you intentionally want an AI diagnosis, and review report paths before sharing outputs because telemetry-derived reports can still reveal workflow or project details.
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
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
Static analysis
No suspicious patterns detected.