lsp-refactor

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No prompt injection or behavior override patterns were detected. The instructions follow a structured, defensive sequence for modifying code.
  • [SAFE]: No data exfiltration or credential harvesting attempts were found. Network operations are limited to the referenced vendor-provided MCP server and standard tool interactions within the workspace.
  • [EXTERNAL_DOWNLOADS]: The skill references a required MCP server from the vendor's repository (github.com/blackwell-systems/agent-lsp). This is a documented dependency for providing the necessary LSP capabilities.
  • [COMMAND_EXECUTION]: The workflow utilizes tools to execute builds and tests (mcp__lsp__run_build, mcp__lsp__run_tests). These operations are used solely for verifying the integrity of the refactor within the local development environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 07:28 AM
Security Audit — agent-trust-hub — lsp-refactor