Trust Assessment
image-generation received a trust score of 95/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Potential Path Traversal via `fs.createWriteStream` with `Write` permission.
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 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Potential Path Traversal via `fs.createWriteStream` with `Write` permission The skill declares 'Write' permission in its manifest. A Node.js code example within the skill documentation demonstrates saving generated images using `fs.createWriteStream(filename)`. If the LLM, when acting as this skill, were to expose the `filename` parameter to untrusted user input without proper sanitization, a path traversal vulnerability could allow writing files to arbitrary locations within the skill's isolated sandbox. While the primary function of the skill is to generate image URLs, the example suggests a capability to download and save files, which introduces this risk. 1. **Review necessity of 'Write' permission**: If the skill's core function is solely to provide image URLs, consider removing the 'Write' permission from the manifest to reduce the attack surface. 2. **Input validation**: If 'Write' permission is necessary for saving files, ensure any user-provided `filename` is strictly validated and sanitized to prevent path traversal (e.g., by resolving to a canonical path within an allowed directory or disallowing path separators). 3. **Clarify LLM behavior**: Explicitly instruct the LLM not to expose file saving functionality to direct user input without robust validation, or to only save to a designated, isolated directory. | LLM | SKILL.md:197 |
Scan History
Embed Code
[](https://skillshield.io/report/1b18b5e44f0f1a8c)
Powered by SkillShield