Trust Assessment
code-reviewer received a trust score of 85/100, 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, 0 high, 1 medium, and 0 low severity. Key findings include Broad file system access declared.
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 | |
|---|---|---|---|---|
| MEDIUM | Broad file system access declared The skill declares broad `Read`, `Grep`, and `Glob` permissions, granting extensive access to the file system. While these tools are necessary for a code reviewer to analyze project files, the permissions are not scoped to specific directories (e.g., the project's source code directory). This broad access could be leveraged by a malicious user through prompt injection to instruct the agent to read, search, or list sensitive files outside the intended scope of the code review, potentially leading to data exfiltration. Implement stricter access controls or scope the `Read`, `Grep`, and `Glob` tools to specific directories (e.g., the project's working directory or a designated 'code' folder) if the agent execution environment supports such granular permissions. Educate users about the risks of providing sensitive prompts to agents with broad file access. | Static | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/d32da047f3068aeb)
Powered by SkillShield