lsp-fix-all

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the Blackwell Systems 'agent-lsp' repository as a necessary dependency.
  • [COMMAND_EXECUTION]: Utilizes the mcp__lsp__apply_edit tool to modify project files. The workflow restricts modifications to standardized 'quickfix' and 'source.organizeImports' actions, avoiding more complex structural changes.
  • [PROMPT_INJECTION]: The skill processes diagnostics and suggested fixes from an LSP server, which constitutes an indirect prompt injection surface.
  • Ingestion points: Data is ingested via mcp__lsp__get_diagnostics and mcp__lsp__suggest_fixes in SKILL.md.
  • Boundary markers: None present.
  • Capability inventory: File modification capabilities are available via mcp__lsp__apply_edit in SKILL.md.
  • Sanitization: The skill implements an explicit whitelist for code actions, only allowing specific low-risk types while rejecting all 'refactor' actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 07:28 AM
Security Audit — agent-trust-hub — lsp-fix-all