Security audit
verify-before-done
Security checks for vulnerabilities and agentic risk
Overview
This skill gives coherent quality-control guidance for verifying work before claiming completion and does not include hidden execution, persistence, credential use, or unrelated data access.
This skill is appropriate to install if you want Codex to be more disciplined about checking work before saying it is finished. It may lead the agent to run relevant tests or inspect logs/files when that fits the task, but the artifact does not add hidden scripts or persistent behavior.
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.