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
Bashtool for running project tests (e.g.,go test) and filtering large output files usinggrep. These are standard procedures for code verification in a developer workspace. - [EXTERNAL_DOWNLOADS]: The skill documentation references a requirement for the
agent-lspMCP 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