Security audit
Corveil
Security checks for vulnerabilities and agentic risk
Overview
This skill openly sets up a local AI gateway that logs routed AI requests, so it is sensitive but disclosed and purpose-aligned.
Install only if you intentionally want Corveil to observe and log AI traffic. Use dev or test provider keys, verify downloaded binaries or installer scripts before running them, avoid routing production secrets through dev mode, and keep track of your original OpenClaw or Claude Code settings so routing can be reverted.
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.