gitnexus-exploring

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local script 'node .gitnexus/run.cjs analyze' to update stale indexes. This involves executing code within the user's workspace.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and analyze untrusted external data (source code and codebase metadata) through GitNexus resources and file reads.
  • Ingestion points: GitNexus protocol resources (e.g., 'gitnexus://repo/{name}/context') and local source files.
  • Boundary markers: None specified in the instructions to distinguish between code content and agent instructions.
  • Capability inventory: Access to tools ('query', 'context'), file system reading, and terminal command execution ('node').
  • Sanitization: No explicit sanitization or filtering of codebase content is mentioned before presenting it to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 01:11 PM
Security Audit — agent-trust-hub — gitnexus-exploring