The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from the Figma REST API, which is an external source that could potentially contain untrusted content.
Ingestion points: Data is fetched via fetch calls to https://api.figma.com as seen in SKILL.md and reference files like references/response-caching.md.
Boundary markers: The provided code snippets do not include specific delimiters or warnings to ignore instructions embedded within the API responses.
Capability inventory: The skill is granted Read, Write, and Edit permissions, enabling the agent to perform file system operations based on the processed API data.
Sanitization: There is no evidence of sanitization or strict schema validation performed on the retrieved JSON payloads in the examples.
[COMMAND_EXECUTION]: The skill includes a shell script example in the Examples section of SKILL.md intended for performance measurement.
Evidence: A bash loop utilizing curl to query the Figma API and measure download sizes and response times.

figma-performance-tuning