The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill involves the agent analyzing external feature components and codebase content to generate UI animations, which creates a potential surface for instructions embedded in data to influence agent behavior.\n
Ingestion points: The skill ingests untrusted data through the optional target argument and the codebase analysis performed during the 'Context Gathering' phase in SKILL.md.\n
Boundary markers: The instructions lack specific requirements for using delimiters or boundary markers (such as XML tags or triple quotes) to isolate external code from the agent's core instructions.\n
Capability inventory: The agent is empowered to modify application code, specifically by implementing CSS transitions, keyframe animations, and JavaScript-based motion logic.\n
Sanitization: There are no defined procedures for sanitizing, escaping, or validating the external codebase content before it is processed by the agent.

animate