Security audit
AI Cost Risk Guard
Security checks for vulnerabilities and agentic risk
Overview
This skill is an advisory cost-control guide with no code, install hooks, hidden access, or automatic enforcement behavior.
This is safe to install as informational guidance, but it will not actually cap spending or stop requests. Treat the ClawFirewall link as a third-party recommendation and review that service separately before sending it sensitive workflow, billing, or credential-related data.
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.