Trust Assessment
shadcn-ui received a trust score of 50/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 4 findings: 2 critical, 2 high, 0 medium, and 0 low severity. Key findings include Dangerous tool allowed: Bash, Excessive Permissions Declared, Direct Bash Command Execution Capability.
The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, dependency_graph, static_code_analysis. The llm_behavioral_safety layer scored lowest at 25/100, indicating areas for improvement.
Last analyzed on February 18, 2026 (commit 51d6d5ab). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Excessive Permissions Declared The skill declares highly privileged permissions including 'Read', 'Write', 'Bash', and 'web_fetch'. 'Bash' allows arbitrary command execution on the host system, 'Read' and 'Write' grant full filesystem access, and 'web_fetch' allows arbitrary network requests. This combination provides an attacker with extensive control over the environment, far exceeding what is typically necessary for a skill providing 'Expert guidance for integrating and building applications with shadcn/ui components'. The broad 'shadcn*:*' and 'mcp_shadcn*' tool access further exacerbates this risk. Review and restrict the 'allowed-tools' to the absolute minimum necessary for the skill's intended functionality. Specifically, consider if 'Bash', 'Write', and 'web_fetch' are truly required. If 'Bash' is needed, ensure all calls are strictly controlled and sanitized, and consider using a more granular tool if available. If 'Read' or 'Write' are needed, restrict them to specific directories or file types. | Unknown | Manifest:1 | |
| CRITICAL | Direct Bash Command Execution Capability The skill explicitly declares 'Bash' as an allowed tool, enabling direct execution of arbitrary shell commands. This is a critical security vulnerability as it allows for command injection if any user input is passed unsanitized to a Bash tool call. The presence of `scripts/verify-setup.sh` demonstrates the intent to execute shell scripts, confirming the active use of this powerful permission. An attacker could craft malicious input to execute arbitrary commands, leading to system compromise, data exfiltration, or denial of service. Remove the 'Bash' permission if not strictly necessary. If 'Bash' is essential, implement robust input validation and sanitization for all arguments passed to Bash commands. Consider using more specific, sandboxed tools instead of direct shell access. Ensure that any shell scripts executed are thoroughly reviewed and do not process untrusted input directly. | Unknown | Manifest:1 | |
| HIGH | Dangerous tool allowed: Bash The skill allows the 'Bash' tool without constraints. This grants arbitrary command execution. Remove unconstrained shell/exec tools from allowed-tools, or add specific command constraints. | Unknown | /tmp/skillscan-clone-bp5flrbo/repo/skills/shadcn-ui/SKILL.md:1 | |
| HIGH | Potential for Data Exfiltration via File System Read and Network Access The combination of 'Read' filesystem permission, 'Bash' command execution, and 'web_fetch' network access creates a high potential for data exfiltration. The `scripts/verify-setup.sh` file demonstrates the capability to read arbitrary file contents (e.g., `grep -q ... tsconfig.json`, `grep -q ... package.json`). An attacker could leverage these permissions to read sensitive files (e.g., configuration files, source code, environment variables) and then transmit them to an external server using `web_fetch` or a `curl` command executed via `Bash`. Restrict 'Read' permissions to only necessary directories and file types. Remove 'web_fetch' if not critical for the skill's core function. If 'web_fetch' is required, ensure all network requests are to trusted, predefined endpoints. Implement strict monitoring and logging of all file system and network activities performed by the skill. | Unknown | Manifest:1 |
Scan History
Embed Code
[](https://skillshield.io/report/4e7547a988ce7e67)
Powered by SkillShield