Trust Assessment
openclaw-security-audit 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 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Unsanitized user input used in shell command.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Unsanitized user input used in shell command The skill's pseudo-code explicitly shows `input.target_config_path` being used directly as an argument to the `cat` command (`raw_config = cat(read_config_path)`). Since `target_config_path` is an optional user-provided input, if it is not properly sanitized, a malicious user could inject arbitrary shell commands (e.g., `'; rm -rf /'`) leading to remote code execution on the host system. Implement robust input validation and sanitization for `target_config_path` to prevent shell metacharacters and path traversal attempts. Ensure the path strictly adheres to expected file path formats. Consider using a safe file reading function provided by the OpenClaw framework or the underlying programming language instead of direct shell execution, or ensure the path is strictly validated to be a file path and not contain any command separators or special characters. | LLM | SKILL.md:61 |
Scan History
Embed Code
[](https://skillshield.io/report/ccd483a3ca6d5772)
Powered by SkillShield