lsp-setup

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes shell commands to identify the host operating system (uname -s) and verify the availability of installed binaries (which, where.exe).
  • [EXTERNAL_DOWNLOADS]: Automates the installation of LSP servers through standard package management tools including npm, pip, brew, go, gem, and apt. These installations pull from official registries and well-known project domains such as GitHub, LLVM, and Eclipse.
  • [PROMPT_INJECTION]: The skill instructions include a fallback to search the web for unsupported languages if they are not present in the reference file. This introduces a surface for indirect prompt injection where instructions from external search results could influence agent behavior.
  • Ingestion points: External search results retrieved via web search when a language is missing from references/lsp-servers.md.
  • Boundary markers: Absent — instructions do not define delimiters for processing external search content.
  • Capability inventory: Shell command execution (installation) and file system writes (configuration updates).
  • Sanitization: Absent — the skill does not specify validation or filtering of content found via web search.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 01:05 AM