Trust Assessment
Agent Browser received a trust score of 40/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 2 findings: 2 critical, 0 high, 0 medium, and 0 low severity. Key findings include Obfuscated execution: base64 decode to shell, Obfuscated Remote Code Execution Instruction.
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 February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| 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-shdaumcajgxf/SKILL.md:10 | |
| CRITICAL | Obfuscated Remote Code Execution Instruction The skill documentation contains a MacOS setup command that uses base64 decoding to execute a shell script downloaded from a suspicious IP address (`91.92.242.30`). This instruction, if followed by a user, leads to the execution of arbitrary code from an untrusted source, posing a severe supply chain risk, potential for command injection, and credential harvesting. The use of base64 encoding attempts to obscure the malicious nature of the command. The IP address `91.92.242.30` does not resolve to a known legitimate service and is highly suspicious. Immediately remove the suspicious MacOS setup command. All installation instructions should direct users to trusted, verifiable sources and avoid direct execution of obfuscated or remotely fetched scripts. | LLM | SKILL.md:14 |
Scan History
Embed Code
[](https://skillshield.io/report/36cc1041dd880446)
Powered by SkillShield