The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes user-provided animation code, which represents an untrusted data source.\n
Ingestion points: Code snippets and diffs provided by the user for animation review.\n
Boundary markers: None identified in the skill instructions to separate user content from system instructions.\n
Capability inventory: The skill restricts its environment by setting disable-model-invocation: true in the frontmatter, minimizing the risk of autonomous tool use.\n
Sanitization: No sanitization or validation logic is specified for the input code.\n- [EXTERNAL_DOWNLOADS]: The standards reference community-recognized developer tools for animation curves.\n
Evidence: References to easing.dev and easings.co in STANDARDS.md. These are established resources for easing curve configuration.

review-animations