Security audit
Creative Agent OS North Star
Security checks for vulnerabilities and agentic risk
Overview
This skill is a small markdown guidance skill for product and architecture review, with no executable code or hidden authority requests.
This skill is appropriate if you want an agent to apply a specific architecture-review lens to creative agent OS decisions. Installing it may bias relevant recommendations toward the included north-star criteria, so users should review those criteria for product fit, but there is no executable or privileged behavior in the inspected artifact.
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.