Trust Assessment
huggingface-papers received a trust score of 77/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Command Injection via Unsanitized User Input in Shell Commands.
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 July 1, 2026 (commit 35e8c35a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Command Injection via Unsanitized User Input in Shell Commands The skill instructions guide the LLM to construct and execute shell commands (using `curl`) with user-provided parameters such as `{PAPER_ID}`, `{AUTHOR_ENTRY_ID}`, and `{USER_ID}`. If a user provides a maliciously crafted paper ID or parameter containing shell metacharacters (e.g., quotes, semicolons, or backticks), it can lead to arbitrary command execution or credential exfiltration (such as leaking the `$HF_TOKEN` environment variable). Instruct the LLM to strictly validate and sanitize all user-provided inputs (e.g., ensuring `{PAPER_ID}` matches the expected arXiv ID pattern `^\d{4}\.\d{4,5}(v\d+)?$`) before interpolating them into shell commands. Alternatively, use a programming language's HTTP library (like Python's `requests` or Node's `fetch`) with parameterized inputs instead of raw shell execution via `curl`. | LLM | SKILL.md:98 |
Scan History
Embed Code
[](https://skillshield.io/report/5f2c2b8ef4540d51)
Powered by SkillShield