Security audit
Openclaw Ceo Review
Security checks for vulnerabilities and agentic risk
Overview
This skill is a planning-review prompt that reads repository context to critique plans, with no evidence of hidden installation, persistence, credential use, exfiltration, or destructive behavior.
Install this if you are comfortable with the agent reading repository history, diffs, TODOs, and project documentation while reviewing a plan. Use it only in projects where that local context is appropriate for the active agent session.
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.