Trust Assessment
decision-trees received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Arbitrary File Read via JSON input, Arbitrary File Write in interactive mode.
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 via JSON input The `scripts/decision_tree.py` script directly uses the value of the `--json` command-line argument as a file path without sanitization. An attacker can provide a path like `/etc/passwd` or `../../sensitive_data.txt` to read arbitrary files on the system, leading to data exfiltration. Sanitize the file path input to ensure it is within expected boundaries (e.g., current working directory or a designated input folder). Alternatively, implement a more secure file handling mechanism or restrict file access permissions for the script. | LLM | scripts/decision_tree.py:107 | |
| HIGH | Arbitrary File Write in interactive mode In the interactive mode of `scripts/decision_tree.py`, the script prompts the user for a filename to save the generated JSON. This input is directly used to open and write to a file without any path sanitization. An attacker can provide a path like `/tmp/malicious.json` or `../../config/settings.json` to write to arbitrary locations on the system, potentially overwriting critical files or injecting malicious content. Sanitize the file path input to ensure it is within expected boundaries (e.g., current working directory or a designated output folder). Alternatively, implement a more secure file handling mechanism or restrict file creation permissions for the script. | LLM | scripts/decision_tree.py:96 |
Scan History
Embed Code
[](https://skillshield.io/report/769ba60733bcd7d3)
Powered by SkillShield