Security audit
Wenyuan Deliberation
Security checks for vulnerabilities and agentic risk
Overview
This is a prompt-only deliberation skill that structures complex decisions and does not request tools, credentials, persistence, or external execution.
This skill appears safe to install as a prompt-only aid for complex decisions. Users should understand that it changes the assistant's answer style by encouraging structured multi-perspective deliberation, and it should not be mistaken for independent multi-model analysis or formal expert review in high-stakes situations.
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