lsp

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a documentation and interface layer for Language Server Protocol (LSP) operations (e.g., diagnostics, go-to-definition, find-references). These tools are invoked through the Model Context Protocol (MCP) interface, not direct shell execution.
  • [SAFE]: No remote dependencies or external scripts are downloaded or executed. The configuration example provided uses standard, well-known language servers like typescript-language-server.
  • [SAFE]: Accessing configuration at ~/.codex/lsp-client.json is a standard practice for development tools and does not constitute unauthorized access to sensitive system credentials or user data.
  • [SAFE]: No patterns of prompt injection, data exfiltration, or obfuscation were detected in the instructions or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 02:19 PM
Security Audit — agent-trust-hub — lsp