The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the user to execute npx gitnexus analyze in the terminal to maintain a fresh index of the codebase.
[EXTERNAL_DOWNLOADS]: The use of the npx command involves downloading the gitnexus package from the public npm registry. This package corresponds to the skill's primary vendor functionality.
[PROMPT_INJECTION]: The skill accepts untrusted data, such as error messages and user-supplied queries, which creates a surface for indirect prompt injection.
Ingestion points: Untrusted data enters the agent context through the query parameter in the gitnexus_query and gitnexus_cypher tools.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat input data as inert or to ignore embedded instructions.
Capability inventory: The skill's tools focus on informational retrieval of code structure, call graphs, and process flows (gitnexus_query, gitnexus_context, gitnexus_cypher).
Sanitization: No input validation or sanitization mechanisms are described for the queries processed by the skill.

gitnexus-debugging