Security Audit

ChromeDevTools/chrome-devtools-mcp:skills/troubleshooting

github.com/ChromeDevTools/chrome-devtools-mcp

AI SkillCommit 3c12a91c3838

CAUTION

Scanned about 22 hours ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

ChromeDevTools/chrome-devtools-mcp:skills/troubleshooting received a trust score of 58/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Potential Command Injection via Unsanitized Error Snippet in Shell Command.

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 September 24, 2026 (commit 3c12a91c). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

70%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings2

Severity	Finding	Layer	Location
CRITICAL	Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains.	Manifest	skills/troubleshooting/SKILL.md:76
HIGH	Potential Command Injection via Unsanitized Error Snippet in Shell Command The troubleshooting skill instructs the LLM to run a shell command (`gh issue list ... --search "<error snippet>"`) using an error snippet obtained from failed tool calls or logs. If the error message contains shell metacharacters (e.g., injected by a malicious website or page being debugged), it can lead to arbitrary command execution when the LLM executes the command in the shell. Instruct the LLM to sanitize the error snippet, extract only alphanumeric keywords for the search query, or avoid executing shell commands with raw, user-controlled error messages.	LLM	SKILL.md:104

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/c6afe32245bffd65.svg)](https://skillshield.io/report/c6afe32245bffd65)