Trust Assessment
middleware-gen 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 Unpinned npm dependency version, User input directly used in LLM prompt for code generation.
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 13, 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 | |
|---|---|---|---|---|
| CRITICAL | User input directly used in LLM prompt for code generation The `description` argument, which is user-provided, is directly embedded into the `user` message sent to the OpenAI API. A malicious user could craft this `description` to perform prompt injection, manipulating the LLM to generate code that deviates from the intended middleware, potentially including malicious logic, or attempting to extract the system prompt or other sensitive information from the LLM. The LLM is instructed to 'Return ONLY the code, no explanation,' but this can often be bypassed by sophisticated prompt injection techniques. The generated code is then written to a file or printed to the console, increasing the risk if the user subsequently executes it. Implement robust input sanitization or validation for the `description` to filter out known prompt injection patterns. Consider using techniques like input parsing, few-shot examples, or more advanced prompt engineering to make the LLM more resilient to manipulation. Educate users about the risks of providing untrusted or malicious descriptions. | LLM | src/index.ts:16 | |
| 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/middleware-gen/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/63ab48951b127862)
Powered by SkillShield