The Agent Skills Directory

[SAFE]: The skill facilitates legitimate codebase exploration and architectural analysis. All identified behaviors align with the stated purpose of helping users or agents understand complex projects.
[EXTERNAL_DOWNLOADS]: The skill recommends running npx gitnexus analyze to refresh the codebase index. This command fetches and executes the gitnexus package from the official npm registry. As this is the primary tool the skill is designed for, it is a standard operational requirement.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes external source code and repository metadata which could contain malicious instructions or misleading comments.
Ingestion points: GitNexus resources (gitnexus://repo/...) and local source files (e.g., src/payments/processor.ts).
Boundary markers: Absent. The skill does not explicitly instruct the agent to use delimiters or treat code content as potentially untrusted data.
Capability inventory: Includes gitnexus_query, gitnexus_context, and file-reading capabilities.
Sanitization: No sanitization or validation of the analyzed source code is performed before the agent processes it.

gitnexus-exploring