Trust Assessment
code-explorer received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Use of broad 'Bash' tool.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Use of broad 'Bash' tool The skill declares the 'Bash' tool, which grants the agent the ability to execute arbitrary shell commands. While this tool is used for core functionality (e.g., `grep`, `find`, `head`, `xargs`) as demonstrated in the skill's workflow and search patterns, its broad nature significantly increases the attack surface for potential command injection vulnerabilities. If user input is not meticulously sanitized and quoted before being incorporated into shell commands, it could lead to unauthorized command execution. Consider if more granular tools (e.g., dedicated `grep` or `find` tools with strict argument validation) could replace `Bash` to reduce the attack surface. If `Bash` is indispensable, ensure all arguments derived from untrusted input are rigorously sanitized and properly quoted to prevent command injection. Implement robust input validation and escaping mechanisms for all shell commands executed via Bash. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/51160598738fa711)
Powered by SkillShield