Trust Assessment
hugging-face-tool-builder received a trust score of 65/100, 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: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include Suspicious import: urllib.request, Prompt Injection Attempt in Skill Definition.
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 11, 2026 (commit 3f4f55d6). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Prompt Injection Attempt in Skill Definition The skill definition attempts to redefine the host LLM's purpose by instructing it to 'create reusable command line scripts and utilities'. This is a direct manipulation of the LLM's core instructions, which constitutes a prompt injection. Remove or rephrase any instructions within the skill definition that attempt to redefine the LLM's purpose or override its primary directives. The skill definition should describe the skill's capabilities, not issue commands to the LLM. | LLM | SKILL.md:4 | |
| 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/hugging-face-tool-builder/references/baseline_hf_api.py:13 |
Scan History
Embed Code
[](https://skillshield.io/report/268bacee662b64ec)
Powered by SkillShield