Security audit

文转粤语音 - Cantonese TTS

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Cantonese text-to-speech helper, with some privacy and dependency cautions but no evidence of deception, persistence, credential access, or destructive behavior.

Install only if you are comfortable using edge-tts for network-backed speech generation. Avoid submitting confidential, regulated, or credential-like text unless external processing is acceptable, and install dependencies in a virtual environment with pinned versions where possible.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: scripts/text_to_cantonese_voice.py:96
Finding: Unpinned Third-Party TTS Dependency Installation
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Note

Location: scripts/text_to_cantonese_voice.py:102
Finding: Undisclosed External Processing of User-Provided Text
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (3)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: 代码的主要功能确实是把输入文本生成粤语语音 MP3，并支持 normal/slow/fast/angry 四种语气，这与描述大体相符。但描述中一个关键承诺是：输入普通话或粤语文字后，会“自动转换为粤语口吻后生成粤语语音”。实际代码没有任何文本转换、翻译、改写或语言风格转换逻辑，只是把原始 text 直接传给 edge_tts.Communicate，并选用 zh-HK 语音合成。因此如果输入是普通话文本，代码并不会先转成粤语表达，而只是用粤语声音朗读原文。这属于功能描述与实际行为的实质性不一致。另有一项轻微差异是代码支持 --voice 指定三种声音，但描述未写出该能力；这通常是未声明的附加能力，不过不如前者关键。综合判断应标记为不匹配。
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The description states the skill will '自动转换为粤语口吻后生成粤语语音MP3', which hard-codes a specific language/locale outcome. This is a natural-language policy concern because the skill does not indicate any user opt-in or alternative language choice, even when the input may be Mandarin text.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This code file contains user-facing natural language that is entirely Chinese in the module docstring and command-line usage, and the script continues this pattern in its runtime messages. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified, which it is not here.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.