The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and refactor source code files, which constitutes an ingestion point for untrusted data. * Ingestion points: Local source code directories (e.g., src/, cmd/) analyzed by the indexion tool. * Boundary markers: The skill does not explicitly define delimiters or warnings to separate the tool's analysis output from the agent's internal reasoning instructions. * Capability inventory: The skill includes commands for file modification (indexion plan unwrap --fix) and code execution (moon test). * Sanitization: No explicit sanitization or validation of the analyzed source code content is performed before processing. This is a standard risk for development tools.

indexion-refactor