Trust Assessment
huggingface-llm-trainer received a trust score of 0/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 12 findings: 4 critical, 6 high, 2 medium, and 0 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), Suspicious import: urllib.request.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on August 1, 2026 (commit 87f9ee5b). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings12
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/huggingface-llm-trainer/scripts/convert_to_gguf.py:55 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/huggingface-llm-trainer/scripts/convert_to_gguf.py:63 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/huggingface-llm-trainer/scripts/convert_to_gguf.py:64 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/huggingface-llm-trainer/scripts/convert_to_gguf.py:81 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_command'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/huggingface-llm-trainer/scripts/convert_to_gguf.py:81 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'check_system_dependencies'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/huggingface-llm-trainer/scripts/convert_to_gguf.py:55 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'check_system_dependencies'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/huggingface-llm-trainer/scripts/convert_to_gguf.py:63 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'check_system_dependencies'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/huggingface-llm-trainer/scripts/convert_to_gguf.py:64 | |
| HIGH | Automatic Job Submission Without User Confirmation The skill instructs the agent to immediately submit training jobs using the hf_jobs() tool without obtaining explicit user confirmation first. Since training jobs run on paid Hugging Face infrastructure and incur financial costs, this directive creates a high risk of unauthorized resource consumption and financial charges if the agent is manipulated via indirect prompt injection (e.g., reading a malicious file or website that instructs it to train a model). Modify the directive in SKILL.md to require explicit user confirmation and cost estimation approval before submitting any training jobs or invoking the hf_jobs() tool. | LLM | SKILL.md:43 | |
| HIGH | Arbitrary Code Execution via trust_remote_code=True The script loads the base model and tokenizer with trust_remote_code=True. This allows arbitrary Python code defined in the model repository to be executed locally. If an attacker can influence the BASE_MODEL or ADAPTER_MODEL environment variables, or if the user is tricked into converting a malicious model, this can lead to remote code execution. Avoid setting trust_remote_code=True unless absolutely necessary and the model source is fully trusted. For standard architectures like Qwen, trust_remote_code is not required in modern transformers versions. | LLM | scripts/convert_to_gguf.py:114 | |
| MEDIUM | Suspicious import: urllib.request Import of 'urllib.request' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/huggingface-llm-trainer/scripts/dataset_inspector.py:24 | |
| MEDIUM | Suspicious import: urllib.request Import of 'urllib.request' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/huggingface-llm-trainer/scripts/hf_benchmarks.py:27 |
Scan History
Embed Code
[](https://skillshield.io/report/8f567a10a6aba17f)
Powered by SkillShield