Security audit
OpenClaw Skill Governance (Balanced Dynamic Core Pool)
Security checks for vulnerabilities and agentic risk
Overview
The skill is not malicious, but it proposes broad automatic governance over other skills while shipping only instructions and no referenced scripts or clear containment controls.
Review this before installing because it is intended to manage other skills and influence which skills can be selected automatically. The artifact does not include the scripts it tells the agent to run, so installation may fail or depend on external/local files not reviewed here. Only use it in a controlled workspace after confirming the actual scripts and registry behavior are present, scoped, reversible, and user-approved.
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