T01 · Skill Instruction Hijacking
- Location
SKILL.md:20- Finding
Forced Promotional Output and Response-Control Hijacking
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This music API skill is not clearly malicious, but it needs review because it sends user content to a third-party service and tries to control error messages, promotions, and raw API log output.
Install only if you intend to use the Miaoyin/Growingth music service and are comfortable sending your lyrics, prompts, titles, task IDs, clip IDs, and API token to that service. Avoid submitting unpublished or confidential material unless you trust the provider, keep the token private, and treat purchase/free-trial messages and raw diagnostic logs as vendor-controlled output rather than independent advice.
SKILL.md:20Forced Promotional Output and Response-Control Hijacking
SKILL.md:157Unsafe Verbatim Disclosure of Remote API Headers and Response Bodies
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
- **Windows PowerShell**: `$env:MIAOYIN_API_TOKEN="your-token"`
- **Windows CMD**: `set MIAOYIN_API_TOKEN=your-token`
- **Docker**: `-e MIAOYIN_API_TOKEN=your-token`
- **.env 文件**: 写入 `MIAOYIN_API_TOKEN=your-token`
⚠️ 任何能设置环境变量的方式都可以,不依赖特定平台。
The manifest describes the skill as a music creation assistant for generating songs, querying tasks, continuing music, and generating lyrics. However, the documented behavior also includes cover/remix generation, merging continuation clips, video generation, WAV conversion, and stem separation, which are materially broader capabilities than the manifest summary.
The trigger description is broad enough that the skill may activate during ordinary music-related conversation and send user content to a third-party API without sufficiently specific intent. In this skill's context, that matters because lyrics, prompts, task IDs, and media-processing requests are transmitted externally, so accidental invocation can create privacy and consent issues.
The skill instructs sending lyrics, prompts, song identifiers, and related metadata to a third-party HTTP API but does not clearly warn users that their content will leave the local system. In a creative-assistant context, users may paste unpublished lyrics or proprietary audio identifiers, so missing disclosure increases the risk of unintended data exposure.
The stated purpose is centered on AI composition and music generation, but the documented API supports post-production audio processing such as accompaniment extraction, multi-stem separation, and de-reverb. These are audio engineering capabilities rather than obvious requirements for composing or generating songs.
All visible user-facing strings in the installer are in Chinese, with no language choice or indication that the skill is region- or language-specific. This can violate language/locale policy when a specific language is imposed without giving users an option.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
echo ""
# 创建目标目录
mkdir -p "$SKILL_DIR"
# 复制所有文件
echo "正在复制文件..."
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
echo ""
# 创建目标目录
mkdir -p "$SKILL_DIR"
# 复制所有文件
echo "正在复制文件..."
L0074 明确写明“中文直接传入”,整体文档和示例也默认要求中文内容处理,但未说明这是区域性工具限制,也未给用户提供语言选择或确认机制。根据自然语言政策要求,强制特定语言/locale 而无用户选择可能构成语言策略违规。
The manifest describes a music creation assistant for songs, tasks, continuation, and lyrics, but the documented APIs also create videos for songs. Video generation is a distinct media-production capability and is not clearly implied by the declared purpose.
This shell script performs a recursive file copy into a directory under the user's home folder, which modifies local files. Although the script prints the target directory and progress, it does not explicitly warn that existing files may be overwritten or changed.
The script tells the user to configure an API token as an environment variable and even persist it in shell startup files, but it does not include any warning that this is sensitive credential material. Missing disclosure around credential handling can lead users to store secrets insecurely or expose them unintentionally.