Security audit
Agent Isolation
Security checks for vulnerabilities and agentic risk
Overview
This prompt-only skill gives disclosed workspace-boundary guidance for multi-agent setups and does not include executable code, hidden access, or network behavior.
Install this if you manage multiple agents on the same machine and want durable workspace separation. Review and adapt the example paths before applying it, because the AGENT.md rules will persist across future sessions and should match your actual agent directories and intended shared folders.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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