gitnexus-exploring

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is configured to download the 'gitnexus' package from the npm registry at runtime using the 'npx -y' command within the MCP server configuration.
  • [REMOTE_CODE_EXECUTION]: The 'mcp.json' file defines an MCP server that executes the 'gitnexus' package directly from the npm registry, which constitutes remote code execution of a third-party dependency.
  • [COMMAND_EXECUTION]: The 'SKILL.md' file instructs the user to run 'npx gitnexus analyze' in the terminal to update stale indexes, which involves executing code downloaded from a remote repository.
  • [PROMPT_INJECTION]: The skill processes data from external codebases through resources like 'gitnexus://repo/{name}/context' and tools like 'gitnexus_query'. This creates a surface for indirect prompt injection if the analyzed repository contains malicious instructions designed to influence the agent's behavior.
  • Ingestion points: Data enters the agent via 'gitnexus://' resource URIs and tool outputs from 'gitnexus_query' and 'gitnexus_context' (SKILL.md).
  • Boundary markers: No specific delimiters or safety instructions are provided to the agent to ignore instructions embedded within the codebase data.
  • Capability inventory: The skill possesses the capability to execute shell commands via 'npx' as defined in 'mcp.json'.
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the repositories before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 11:58 AM