ClawHub
Back to skill

Security audit

Alibaba Cloud AI Audio LiveTranslate

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Alibaba Qwen LiveTranslate helper that writes local request/evidence files, with no artifact-backed sign of deception, exfiltration, or unsafe persistence.

Before installing, confirm you are comfortable with translation request payloads and response summaries being saved locally under output/aliyun-qwen-livetranslate/. Avoid using it for confidential conversations unless you have a retention and cleanup process for those files.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill performs file-write operations during validation and instructs saving request payloads and response summaries to disk, but it does not declare any explicit tool scope such as permissions or allowed-tools. This creates a capability/manifest mismatch that can lead to unintended execution in environments that rely on metadata for policy enforcement or user consent.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly says translation session payloads and response summaries should be saved under an output directory, but the skill description does not warn users that potentially sensitive speech-derived content may be persisted to disk. In a live translation context, saved payloads can contain transcripts, meeting content, personal data, or business-sensitive information, increasing confidentiality and retention risk.

Natural-Language Policy Violations

Low
Confidence
86% confidence
Finding
The script defaults to translating from Chinese to English via hard-coded language arguments. This creates a natural-language locale preference without asking the user to choose or clearly limiting the tool to a region-specific use case.

Static analysis

No suspicious patterns detected.