The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes npx hyperframes to perform various diagnostic and verification tasks, including linting, keyframe analysis, and generating visual snapshots or ghosts for debugging.
[EXTERNAL_DOWNLOADS]: The use of the npx command results in the retrieval and execution of the hyperframes package from the public NPM registry.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to translate user-provided animation descriptions into functional code, which creates a potential surface for indirect injection if user input is not properly handled by the agent.
Ingestion points: User-provided animation requests and visual descriptions described in the 'Creator editing boundary' section of SKILL.md.
Boundary markers: None identified in the instructional text for separating user input from system instructions.
Capability inventory: Execution of CLI commands via npx as outlined in the 'CLI Proof' section of SKILL.md.
Sanitization: There are no explicit instructions for the agent to sanitize or validate user-provided parameters (like selectors or timings) before incorporating them into shell commands.

hyperframes-keyframes