lsp-dead-code

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute search commands using the grep utility. This is intended to verify symbol references in wiring files and registration contexts that might be overlooked by static LSP analysis, ensuring accuracy before code removal.
  • [EXTERNAL_DOWNLOADS]: The documentation references the agent-lsp repository on GitHub (github.com/blackwell-systems/agent-lsp) as a required component. This repository is maintained by the skill's author and serves as the primary provider for the LSP tools used in the analysis.
  • [PROMPT_INJECTION]: The skill processes untrusted code content and symbol identifiers, creating an indirect prompt injection surface. 1. Ingestion points: Symbol names and file paths via mcp__lsp__list_symbols. 2. Boundary markers: Absent. 3. Capability inventory: Code deletion via mcp__lsp__safe_delete_symbol and shell commands via grep. 4. Sanitization: The skill mitigates risks by requiring manual verification and explicit user confirmation before any destructive actions are performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 07:28 AM
Security Audit — agent-trust-hub — lsp-dead-code