Trust Assessment
qwen3-tts-instruct received a trust score of 74/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 2 medium, and 0 low severity. Key findings include Unpinned Python Dependencies, Arbitrary File Read via --input-file, Arbitrary File Write via --output.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Arbitrary File Read via --input-file The `scripts/tts.py` skill allows reading text from an arbitrary file specified by the `--input-file` argument. If the AI agent executes this skill with a user-controlled file path, it could be coerced into reading sensitive system files (e.g., `/etc/passwd`, `/root/.ssh/id_rsa`) and potentially exfiltrating their contents. Restrict file access to a designated, sandboxed directory. Implement strict input validation for file paths, disallowing absolute paths or paths containing directory traversal sequences (`../`). Consider using a file picker or content ID instead of direct file paths. | LLM | scripts/tts.py:1039 | |
| MEDIUM | Unpinned Python Dependencies The `scripts/setup.sh` installs Python packages (`dashscope`, `websocket-client`, `soundfile`) without specifying exact versions. This can lead to supply chain vulnerabilities if a new version of a dependency introduces breaking changes, security flaws, or malicious code. It also makes builds non-reproducible. Pin all Python dependencies to exact versions (e.g., `pip install dashscope==1.2.3`). It is recommended to use a `requirements.txt` file for managing dependencies. | LLM | scripts/setup.sh:90 | |
| MEDIUM | Arbitrary File Write via --output The `scripts/tts.py` skill allows writing the generated audio to an arbitrary file path specified by the `--output` argument. If the AI agent executes this skill with a user-controlled file path, it could be coerced into overwriting or creating files in sensitive system locations (e.g., `/etc/cron.d/`, `/var/www/html/`) if the agent has sufficient write permissions. Restrict file write access to a designated, sandboxed directory. Implement strict input validation for file paths, disallowing absolute paths or paths containing directory traversal sequences (`../`). Ensure the AI agent runs with minimal necessary file system permissions. | LLM | scripts/tts.py:1000 |
Scan History
Embed Code
[](https://skillshield.io/report/e37e29ddec067b96)
Powered by SkillShield