Trust Assessment
security-reviewer 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 Excessive 'Bash' permission granted.
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 June 1, 2026 (commit e8be415b). 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 | Excessive 'Bash' permission granted The skill declares 'Bash' as an allowed tool in its manifest. This permission grants the ability to execute arbitrary shell commands, which is a critical security risk. It enables command injection, data exfiltration, and potential system compromise if exploited. While a security reviewer skill might require running external tools, direct 'Bash' access is a high-risk capability that should be carefully evaluated. This permission, combined with 'Read', 'Grep', and 'Glob', allows for broad filesystem access and the execution of arbitrary code, creating a significant attack surface. Re-evaluate the necessity of direct 'Bash' access. If external tools are required, consider wrapping them in more specific, sandboxed tools or APIs rather than granting raw shell access. Implement strict input sanitization for any user-controlled data passed to shell commands. Restrict the scope of 'Read', 'Grep', and 'Glob' to only necessary directories and implement robust sandboxing for the execution environment. | LLM | Manifest |
Scan History
Embed Code
[](https://skillshield.io/report/c69c07edc08d9a84)
Powered by SkillShield