gitnexus-exploring
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow includes an instruction to execute a local script ('node .gitnexus/run.cjs analyze') if the code index is stale. This involves executing code from a file located within the project's hidden .gitnexus directory.
- [PROMPT_INJECTION]: The skill processes untrusted data from the codebase being explored (via gitnexus:// resources and direct file reading). This creates an indirect prompt injection surface where malicious instructions embedded in code comments or documentation could influence agent behavior.
- Ingestion points: Files and metadata accessed through gitnexus://repo/{name}/context, gitnexus://repo/{name}/process/{name}, and source files.
- Boundary markers: None present; the instructions do not provide delimiters or guidance to ignore potential instructions within analyzed code.
- Capability inventory: The agent has access to terminal execution and code exploration tools.
- Sanitization: No sanitization or filtering of codebase content is mentioned in the skill instructions.
Audit Metadata