Security audit

Alibaba Cloud AI Multimodal QVQ

Security checks for vulnerabilities and agentic risk

Overview

This is a small, coherent Alibaba QVQ visual-reasoning helper with only minor documentation and least-privilege metadata issues.

Before installing, note that this skill is mainly a request-template helper, not a full Alibaba Cloud integration. Review or correct the mismatched validation path if you rely on automated validation, and keep generated output paths constrained to the intended output directory.

A.I.G

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

SkillSpector

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 (1)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 82% confidence
Finding: The skill includes commands that write files under output/aliyun-qvq/ but does not declare any explicit tool scope such as permissions or allowed-tools. This creates a mismatch between documented behavior and declared capabilities, which can lead to over-broad execution in agent environments and reduce the effectiveness of policy enforcement or review.
Content: No source excerpt is available for this finding.