Trust Assessment
gemini-image-simple received a trust score of 59/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 4 findings: 0 critical, 2 high, 2 medium, and 0 low severity. Key findings include Suspicious import: urllib.request, Potential data exfiltration: file read + network send, Arbitrary file read and exfiltration to external API.
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 Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential data exfiltration: file read + network send Function 'generate_image' reads files and sends data over the network. This may indicate data exfiltration. Review this function to ensure file contents are not being sent to external servers. | Static | skills/cluka-399/gemini-image-simple/scripts/generate.py:116 | |
| HIGH | Arbitrary file read and exfiltration to external API The skill allows reading arbitrary files from the filesystem via the `--input` argument. The content of these files is base64 encoded and sent to the Google Gemini API as part of the image editing request. An attacker could use this to exfiltrate sensitive files (e.g., `/etc/passwd`, `~/.ssh/id_rsa`, configuration files) from the system where the skill is executed, by crafting a malicious `--input` path. Restrict the `--input` argument to a specific, sandboxed directory (e.g., a temporary directory or a user-specific upload directory). Implement strict validation of file paths to prevent directory traversal attacks (e.g., `../`). Consider using a more secure file access mechanism if available in the execution environment. | LLM | scripts/generate.py:30 | |
| 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/cluka-399/gemini-image-simple/scripts/generate.py:16 | |
| MEDIUM | Arbitrary file write to filesystem The skill allows writing generated images to an arbitrary path specified by the `output` argument. If the skill runs with elevated permissions, a malicious actor could instruct the skill to write to sensitive system locations (e.g., `/etc/cron.d/`, `/usr/local/bin/`) or overwrite existing system files, potentially leading to indirect command injection or denial of service. While the content written is an image, overwriting critical files with image data can still cause system instability or lead to further exploits. Restrict the `output` argument to a specific, sandboxed output directory. Implement strict validation of file paths to prevent directory traversal attacks. | LLM | scripts/generate.py:90 |
Scan History
Embed Code
[](https://skillshield.io/report/ba3380cb0591a7df)
Powered by SkillShield