The Agent Skills Directory

[SAFE]: No malicious behavior detected. The skill provides a clear methodology for animation analysis and uses standard web technologies for its viewer tool.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests data from external web pages and source code to populate an animation timeline.
Ingestion points: External data is written to timeline.js (specifically the preview.html and preview.css fields) by the agent.
Boundary markers: No explicit delimiters or warnings are used to sequester this external data within the generated file.
Capability inventory: The skill includes a viewer.html tool that renders the extracted data. The agent is capable of writing the data file used by this viewer.
Sanitization: The viewer.html tool uses innerHTML to render the extracted properties without sanitization. However, this is consistent with the tool's purpose as a developer utility for local animation analysis.

deconstruct