Security audit
Deep Planning Skill
Security checks for vulnerabilities and agentic risk
Overview
This is an instruction-only planning skill that asks the agent to produce better plans using an isolated, tool-free subagent, without hidden installation, persistence, or data access behavior.
Install this if you want a structured deep-planning workflow for complex design or research tasks. Expect higher latency and possible extra subagent/model usage, but the artifact does not request local file access, credentials, network access, or persistent system changes.
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.