Security audit
Auto Skill Trigger
Security checks for vulnerabilities and agentic risk
Overview
This skill only suggests relevant skills by keyword matching and does not add executables, network access, credentials, or hidden data handling.
Before installing, understand that this skill can steer the agent toward a subset of skills based on keyword matches. That is its intended function, but you may want to tune or disable it if automatic skill hints cause the agent to overlook better tools.
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.