lsp-setup

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's Behavior explicitly instructs the agent to "search the web for ' LSP server'" when a language is missing from the bundled references (see the Behavior section of SKILL.md), which requires fetching and interpreting open/public third-party web pages (e.g., GitHub releases, download sites) and using that information to decide installation/configuration steps.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). This skill explicitly runs install commands that fetch and execute remote LSP binaries as required runtime dependencies (e.g., downloading Eclipse JDT LS from https://download.eclipse.org/jdtls/milestones/), so external content downloaded at runtime can execute code.