The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local script node .gitnexus/run.cjs analyze to update the codebase index. This is a standard operation for local-first development tools.\n- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes and refactors codebase content which could contain malicious instructions.\n
Ingestion points: External codebase data is ingested via tools such as rename, impact, query, and context.\n
Boundary markers: No specific delimiters or safety warnings to ignore instructions embedded in the code are present.\n
Capability inventory: The skill can modify the filesystem through the rename tool and execute local shell commands.\n
Sanitization: The instructions do not specify any sanitization or validation of the code content before analysis or modification.

gitnexus-refactoring