The Agent Skills Directory

[UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill requires the installation of the requests library from the Python Package Index (PyPI). It also references a local implementation script scripts/figma-export.py that is executed via the shell, though the script itself was not provided in the skill package.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Figma URLs provided as input, which creates a surface for indirect prompt injection. Ingestion points: The <figma_url> parameter in SKILL.md. Boundary markers: Absent; there are no instructions to the agent to treat the external content as untrusted. Capability inventory: The skill has capabilities for network communication (Figma API) and file system writes (image output). Sanitization: Unverifiable due to the missing implementation script.

figma-export