Security Audit
ChromeDevTools/chrome-devtools-mcp:skills/memory-leak-debugging
github.com/ChromeDevTools/chrome-devtools-mcpTrust Assessment
ChromeDevTools/chrome-devtools-mcp:skills/memory-leak-debugging received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Reading MCP configuration file risks credential exposure.
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
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Reading MCP configuration file risks credential exposure The skill instructs the LLM to read the MCP configuration file to check if the `--memoryDebugging` flag is enabled. MCP configuration files (such as `claude_desktop_config.json`) typically contain sensitive environment variables, API keys, and access tokens for various services. Reading this file exposes these credentials to the LLM context, posing a significant credential harvesting and data leakage risk. Avoid instructing the LLM to read the global or local MCP configuration files. Instead, the LLM should determine tool availability by inspecting the list of registered tools or by attempting to call the tool and handling any unsupported tool errors gracefully. | LLM | SKILL.md:9 |
Scan History
Embed Code
[](https://skillshield.io/report/3780efb77104e4e2)
Powered by SkillShield