The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface common to coding assistants, as it is designed to ingest and analyze untrusted project source code.
Ingestion points: The agent is instructed in SKILL.md (Phase 1) to scan the project structure, specifically files within the app/ and components/ directories.
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following malicious instructions that might be embedded in the analyzed source code files.
Capability inventory: The skill is capable of modifying the project's tailwind.config.ts, creating new files for hooks, and updating existing components in the file system.
Sanitization: No specific sanitization or validation mechanisms are defined for the code content being analyzed.
[COMMAND_EXECUTION]: The skill provides documentation on project analysis, including a visual representation of a directory tree in references/component-checklist.md, but it does not execute arbitrary shell commands.
[EXTERNAL_DOWNLOADS]: The skill mentions common, well-known frontend libraries such as framer-motion, gsap, and react-intersection-observer, which are standard dependencies for the stated purpose of UI animation.

frontend-ui-animator