Security audit
Supervising Agents
Security checks for vulnerabilities and agentic risk
Overview
This is an instruction-only skill for supervising delegated agent work, and its checks and messaging guidance fit that purpose.
Install this if you want a more assertive workflow for managing subagents. Keep its file and command checks limited to the relevant project workspace, and be aware that enabling it as a default skill may make your agent supervise delegated tasks more aggressively across sessions.
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.