gitnexus-debugging
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the user to run
npx gitnexus analyzein the terminal to update the index. This is a standard tool execution consistent with the skill's purpose of analyzing codebases. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data (code search results, call chains, and source file content) which represents an attack surface for indirect prompt injection if the scanned codebase contains malicious instructions.
- Ingestion points: Untrusted data enters the agent context through
gitnexus_queryresults,gitnexus_contextmetadata, and source code read via thegitnexus://URI scheme. - Boundary markers: None identified in the skill instructions to distinguish between tool output and data content.
- Capability inventory: The skill possesses capabilities for querying code structure, reading repository files, and executing custom Cypher queries.
- Sanitization: No specific sanitization or filtering of codebase content is mentioned before it is presented to the agent.
Audit Metadata