gitnexus-exploring

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user or agent to execute node .gitnexus/run.cjs analyze to refresh the index if it is reported as stale. This involves running a JavaScript file from a hidden directory within the project workspace.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it is designed to ingest and analyze untrusted codebase data.
  • Ingestion points: The skill reads codebase overview, stats, and functional clusters via gitnexus:// URI resources and reads implementation details directly from source files (e.g., src/payments/processor.ts).
  • Boundary markers: Absent. There are no explicit instructions to the agent to treat the code content as data only or to ignore instructions embedded within the code comments or strings.
  • Capability inventory: The skill environment allows for shell command execution (node).
  • Sanitization: Absent. The skill does not define any filtering, validation, or escaping mechanisms for the content it retrieves from the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 02:34 AM
Security Audit — agent-trust-hub — gitnexus-exploring