Trust Assessment
torch-geometric received a trust score of 60/100, 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, 1 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Path Traversal in File Write Operation.
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 458b1186). 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 | Path Traversal in File Write Operation The script `create_gnn_template.py` uses user-provided input for the output file path without proper sanitization. An attacker can use path traversal sequences (e.g., `../`) in the `--output` argument to write generated code to arbitrary locations on the filesystem where the script has write permissions. This could lead to overwriting critical system files or placing malicious scripts in unexpected directories. Sanitize the `output` argument to prevent path traversal. Ensure that the generated file is written only within an intended, controlled directory. This can be achieved by normalizing the path and verifying it remains within a designated output folder, or by only accepting a filename and prepending a secure base directory. | Static | scripts/create_gnn_template.py:139 | |
| HIGH | Path Traversal in File Write Operation The script `visualize_graph.py` uses user-provided input for the output image file path without proper sanitization. An attacker can use path traversal sequences (e.g., `../`) in the `--output` argument to write image files to arbitrary locations on the filesystem where the script has write permissions. This could lead to overwriting critical system files or placing malicious content in unexpected directories. Sanitize the `output_path` argument to prevent path traversal. Ensure that the generated image file is written only within an intended, controlled directory. This can be achieved by normalizing the path and verifying it remains within a designated output folder, or by only accepting a filename and prepending a secure base directory. | Static | scripts/visualize_graph.py:160 | |
| MEDIUM | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | cli-tool/components/mcps/devtools/figma-dev-mode.json:4 | |
| LOW | Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | cli-tool/components/mcps/devtools/jfrog.json:4 |
Scan History
Embed Code
[](https://skillshield.io/report/9ff04da0d92ab940)
Powered by SkillShield