The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown documentation and React code snippets illustrating design patterns. No malicious behavior, command execution, or data exfiltration patterns were identified.
[INDIRECT_PROMPT_INJECTION]: The skill involves the analysis and refactoring of project source files and package configuration.
Ingestion points: Reads package.json and React component source files as instructed in house-rules.md.
Boundary markers: None explicitly defined for untrusted code segments.
Capability inventory: File creation and modification for component authoring and refactoring.
Sanitization: Not present.
Note: As per safety guidelines, this attack surface is noted as a standard requirement for the skill's purpose.

composable-components