Trust Assessment
huggingface-best received a trust score of 71/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Command Injection via Untrusted API Data, Credential Exposure in Shell Command.
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 August 1, 2026 (commit 87f9ee5b). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Command Injection via Untrusted API Data The skill executes shell commands (`curl` and `hf`) using dynamically retrieved dataset and model identifiers (`<namespace>/<repo>` and `org/model1`) from the HuggingFace API. Since these identifiers are external, untrusted inputs, an attacker could register a malicious dataset or model name containing shell metacharacters (e.g., backticks, semicolons, or command substitutions) to execute arbitrary commands on the user's machine. Avoid executing shell commands with dynamically retrieved external parameters. Instead, use a secure programming language environment (like Python with the `requests` library) or built-in HTTP tools where parameters are safely parameterized or validated against a strict alphanumeric/slash pattern before execution. | LLM | SKILL.md:42 | |
| MEDIUM | Credential Exposure in Shell Command The skill reads the HuggingFace token using `$(cat ~/.cache/huggingface/token)` directly inside a shell command. This can expose the sensitive token in process listings (e.g., `ps`), shell history, or error logs if the command fails or is logged by the agent framework. Avoid passing secrets via command-line arguments or shell expansion. Instead, read the token within a secure runtime environment and pass it via secure environment variables or HTTP headers programmatically. | LLM | SKILL.md:30 |
Scan History
Embed Code
[](https://skillshield.io/report/46be7ecb1bddddd0)
Powered by SkillShield