Trust Assessment
Agent Browser received a trust score of 35/100, 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: 2 critical, 1 high, 0 medium, and 0 low severity. Key findings include Obfuscated execution: base64 decode to shell, Hidden Instruction: Arbitrary Code Execution via Base64 encoded script, Supply Chain Risk: Untrusted Executable Download.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on February 12, 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 | Obfuscated execution: base64 decode to shell Detected base64-encoded data being decoded and piped to a shell interpreter. This is a common obfuscation technique. Decode and inspect the base64 content before execution. | Static | skills/sakaen736jih/agent-browser-ha2gvrwrmbil/SKILL.md:10 | |
| CRITICAL | Hidden Instruction: Arbitrary Code Execution via Base64 encoded script The skill instructs users to execute a base64-decoded shell command that downloads and runs an arbitrary script from an untrusted IP address (91.92.242.30). This constitutes a severe command injection and supply chain risk, allowing for potential malware installation, data exfiltration, or complete system compromise. Immediately remove the instruction to execute the base64-encoded command. Never instruct users to download and execute scripts from untrusted or unverified sources. Provide a secure, verifiable installation method for any required dependencies. | LLM | SKILL.md:13 | |
| HIGH | Supply Chain Risk: Untrusted Executable Download The skill instructs users to download and run an executable (`OpenClawProvider-1.0.2.zip`) from a personal GitHub repository (syazema/OpenClawProvider) with a hardcoded password ('openclaw'). This poses a significant supply chain risk as the source is not officially verified, and the executable could contain malicious code. Running such an executable grants it full system access. Replace the instruction with a link to an officially verified and trusted source for the `OpenClawProvider` package, or provide clear instructions on how to build it from a trusted source. Avoid distributing executables from personal, unverified repositories, especially with hardcoded passwords. | LLM | SKILL.md:9 |
Scan History
Embed Code
[](https://skillshield.io/report/171e807b9d8469be)
Powered by SkillShield