Security audit
Ibuildbots Verify
Security checks for vulnerabilities and agentic risk
Overview
This skill is a transparent local prompt-injection test guide for agents and does not package hidden code or request unexpected access.
Before installing, understand that the skill points you to clone and run an external GitHub harness locally. Review that repository before execution, use a test agent command, set a reasonable timeout, and avoid connecting production credentials or high-impact tools during the robustness test.
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.