Security audit
invariant-guarded-debugging
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed debugging discipline that tells the agent to make smaller, safer, reversible changes with checks and rollback.
This skill is appropriate if you want a coding agent to slow down around risky debugging work, protect known-good components, and prove changes with checks. Before installing, note that it may make the agent run more verification commands or ask for stronger evidence around live services, databases, or APIs when those are relevant to the task.
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.