Security audit
AI Common Sense
Security checks for vulnerabilities and agentic risk
Overview
This appears to be a design-skill directory guide with optional third-party install commands, not a skill that secretly runs code or handles sensitive data.
Use this as a reference guide. Before running any listed git clone command, inspect the linked repository, prefer pinned commits or trusted releases, and install only the specific design skills you intentionally want added to your local agent environment.
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.