Trust Assessment
upload-gen received a trust score of 87/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Unpinned npm dependency version, Prompt Injection Vulnerability in Target LLM.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Unpinned npm dependency version Dependency 'commander' is not pinned to an exact version ('^12.1.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/lxgicstudios/upload-gen/package.json | |
| MEDIUM | Prompt Injection Vulnerability in Target LLM The skill directly incorporates user-provided input (`description`) into the 'user' message of an OpenAI API call without sanitization or robust input validation. This creates a direct prompt injection vector for the target LLM (gpt-4o-mini). A malicious user could craft the 'description' argument to manipulate the target LLM's behavior, override system instructions, attempt to extract information, or generate unintended/malicious code. Implement robust input validation and sanitization for the 'description' argument. Consider using techniques like input filtering, escaping, or more advanced prompt engineering strategies (e.g., separating user input with clear delimiters, using few-shot examples to reinforce desired behavior, or employing a separate moderation LLM) to mitigate prompt injection risks. While the system prompt provides some guardrails, direct user input to the 'user' role remains a significant risk. | LLM | src/index.ts:10 |
Scan History
Embed Code
[](https://skillshield.io/report/d85519c50e853355)
Powered by SkillShield