claude-code-ultimate-guide

Warn

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing and running an MCP server using the command npx -y claude-code-ultimate-guide-mcp, which fetches and executes code from the public NPM registry at runtime.
  • [PROMPT_INJECTION]: Under the 'Interactive Onboarding' section, the skill instructs the agent to 'Fetch and follow the onboarding instructions' from https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/tools/onboarding-prompt.md. This represents an indirect prompt injection surface where the agent's operating instructions are retrieved from an external, mutable source (GitHub) rather than being fixed within the skill manifest.
  • [REMOTE_CODE_EXECUTION]: The installation process involving npx results in the execution of remotely hosted code on the local machine as part of the setup for the recommended MCP server.
  • [PROMPT_INJECTION]: Static analysis detected prompt injection keywords such as 'ignore previous instructions'; however, these are located within an educational Python snippet intended to demonstrate input sanitization for security hardening and do not indicate a malicious override attempt.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 17, 2026, 09:14 AM
Security Audit — agent-trust-hub — claude-code-ultimate-guide