gitnexus-guide

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The configuration in mcp.json uses npx to fetch and execute the gitnexus package from the NPM registry at runtime. This is standard behavior for the tool's intended use.\n- [COMMAND_EXECUTION]: The server configuration executes npx gitnexus@latest mcp to initialize the service. The documentation also instructs users to run npx gitnexus analyze in the terminal to update the codebase index.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes external codebase data.\n
  • Ingestion points: Code context and execution traces are ingested through gitnexus://repo/ resources and tool outputs such as query and impact (SKILL.md).\n
  • Boundary markers: None defined. The skill does not use specific delimiters to distinguish between repository content and instructions.\n
  • Capability inventory: The skill can execute commands in the terminal (analyze) and query repository data (mcp.json, SKILL.md).\n
  • Sanitization: Absent. No specific sanitization or filtering logic for codebase content is described in the skill files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 04:55 PM