Trust Assessment
Vision Sandbox received a trust score of 79/100, 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, 1 high, 1 medium, and 0 low severity. Key findings include Unpinned Python dependency version, Arbitrary file read and transmission to third-party 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 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 | |
|---|---|---|---|---|
| HIGH | Arbitrary file read and transmission to third-party API The skill reads the content of any file specified by the `--image` argument and transmits it to the Google Gemini API. While the skill is intended for images, it does not perform robust file type validation beyond a basic suffix check for MIME type. The `types.Part.from_bytes` function will send the raw bytes of any file, regardless of its actual content or the inferred MIME type. This allows a user to potentially exfiltrate the content of arbitrary local files (e.g., configuration files, private keys) to Google's servers via the Gemini API. Implement robust file type validation (e.g., by checking file headers/magic bytes using a library like `python-magic`) to ensure that only actual image files are read and transmitted. Alternatively, restrict the `image_path` to a specific, isolated directory or enforce strict file extension whitelisting. | LLM | scripts/vision_executor.py:25 | |
| MEDIUM | Unpinned Python dependency version Dependency 'google-genai>=1.0.0' is not pinned to an exact version. Pin Python dependencies with exact versions where feasible. | Dependencies | skills/johanesalxd/vision-sandbox/pyproject.toml |
Scan History
Embed Code
[](https://skillshield.io/report/4054b57971785c70)
Powered by SkillShield