Trust Assessment
browser-use received a trust score of 12/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 3 critical, 0 high, 0 medium, and 0 low severity. Key findings include Remote code execution: curl/wget pipe to shell, Unsafe use of BROWSER_USE_API_KEY in shell commands.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 40/100, indicating areas for improvement.
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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/jfrux/browser-use-api/scripts/browser-use.sh:29 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/jfrux/browser-use-api/scripts/browser-use.sh:51 | |
| CRITICAL | Unsafe use of BROWSER_USE_API_KEY in shell commands The `BROWSER_USE_API_KEY` environment variable is directly interpolated into double-quoted strings within `curl` commands. If the value of `BROWSER_USE_API_KEY` contains shell metacharacters (e.g., a double quote `"`, semicolon `;`, or backtick `` ` ``), it can break out of the string and allow for arbitrary command injection. This could lead to data exfiltration (e.g., sending local files or other environment variables to an attacker-controlled server) or execution of malicious commands on the host system. This vulnerability exists in all `curl` calls that use the API key. Avoid direct interpolation of sensitive environment variables into shell commands without robust escaping. Ensure the `BROWSER_USE_API_KEY` is sanitized to prevent shell metacharacters from breaking out of the string context. Consider using a safer method for passing secrets, such as a dedicated tool or a programming language's subprocess module that avoids shell interpretation. If strictly using bash, ensure the API key is validated to contain only safe characters, or implement a robust escaping mechanism for all possible shell metacharacters. | LLM | scripts/browser-use.sh:26 |
Scan History
Embed Code
[](https://skillshield.io/report/ee288b412c101d1c)
Powered by SkillShield