Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
- Without declared permissions the skill's intent is opaque and cannot be validated.
Security audit
Alibaba Cloud AI Multimodal Qwen Omni
Security checks for vulnerabilities and agentic risk
Overview
This is a simple Alibaba Qwen Omni helper skill with a local request-payload script and no hidden high-impact behavior.
Review the generated request payload before use, especially the default instruction to answer in Chinese and the example image URL. Installing this skill does not appear to grant hidden persistence, credential access, or broad local authority.
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
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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
Findings (2)
Natural-Language Policy Violations
Medium
- Confidence
- 96% confidence
- Finding
- The default payload instructs the model to 'answer in Chinese,' which imposes a specific language on all outputs. This is a natural-language locale policy issue because the script does not offer user opt-in, selection, or any documented reason for forcing that language.
Static analysis
No suspicious patterns detected.