Trust Assessment
blender-pipeline received a trust score of 35/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 5 findings: 1 critical, 2 high, 2 medium, and 0 low severity. Key findings include Persistence / self-modification instructions, Sensitive environment variable access: $HOME, Persistence mechanism: Shell RC file modification.
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 Findings5
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/kjaylee/blender-pipeline/SKILL.md:227 | |
| HIGH | Arbitrary Code Execution via Malicious Blender Files The skill's Python scripts (e.g., `convert_format.py`, `render_sprite_sheet.py`) are designed to import or open 3D asset files, including `.blend` files, provided by the user. If the Blender instance running on the target machine (e.g., 'MiniPC' as described in SKILL.md) has the 'Auto Run Python Scripts' preference enabled, a specially crafted malicious `.blend` file could execute arbitrary Python code on the system when opened or imported by the skill. This poses a significant command injection risk, as the skill's core function involves processing untrusted external 3D assets. Ensure that the Blender environment used by the skill has the 'Auto Run Python Scripts' preference disabled. This is a critical security measure when processing untrusted `.blend` files. Additionally, consider running Blender in a sandboxed or containerized environment to limit potential damage from any exploited vulnerabilities. | LLM | scripts/convert_format.py:68 | |
| HIGH | Arbitrary Code Execution via Malicious Blender Files (render_sprite_sheet.py) Similar to `convert_format.py`, the `render_sprite_sheet.py` script also includes functionality to import 3D files, including `.blend` files, using `bpy.ops.wm.open_mainfile`. If the Blender instance on the target machine has 'Auto Run Python Scripts' enabled, a malicious `.blend` file provided via the `--import` argument could execute arbitrary Python code, leading to command injection. Ensure that the Blender environment used by the skill has the 'Auto Run Python Scripts' preference disabled. This is a critical security measure when processing untrusted `.blend` files. Additionally, consider running Blender in a sandboxed or containerized environment to limit potential damage from any exploited vulnerabilities. | LLM | scripts/render_sprite_sheet.py:100 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/kjaylee/blender-pipeline/SKILL.md:227 | |
| MEDIUM | Persistence mechanism: Shell RC file modification Detected Shell RC file modification pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/kjaylee/blender-pipeline/SKILL.md:227 |
Scan History
Embed Code
[](https://skillshield.io/report/490f4f8f792f75f8)
Powered by SkillShield