lsp-verify

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions include the use of shell commands via the Bash tool for running project tests (e.g., go test) and filtering large output files using grep. These are standard procedures for code verification in a developer workspace.
  • [EXTERNAL_DOWNLOADS]: The skill documentation references a requirement for the agent-lsp MCP server, pointing to a GitHub repository (github.com/blackwell-systems/agent-lsp) owned by the skill's author. This is a legitimate dependency for the skill's advertised functionality.
  • [PROMPT_INJECTION]: The skill processes untrusted data from the local workspace, specifically LSP diagnostics and test runner outputs, to generate reports and suggest code fixes. This creates a surface for indirect prompt injection if malicious instructions are embedded in diagnostic messages or test failures.
  • Ingestion points: LSP diagnostic output and test runner results (referenced in SKILL.md).
  • Boundary markers: None identified.
  • Capability inventory: Shell execution (Bash) and file modification (mcp__lsp__apply_edit).
  • Sanitization: None identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 07:28 AM
Security Audit — agent-trust-hub — lsp-verify