Security audit
Multi-Agent Filesystem Governance
Security checks for vulnerabilities and agentic risk
Overview
This skill is a coherent filesystem-organization guide with no code, network behavior, credential handling, or hidden execution.
This skill is suitable as a policy aid for organizing files across agents. Before installing, note that it may influence where agents choose to create, move, or archive files, but its own instructions emphasize narrow scope, non-destructive choices, and avoiding shared writes unless reuse is intentional.
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
Static analysis
No suspicious patterns detected.