The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and process untrusted data from an external codebase, including CSS files and design tokens.
Ingestion points: The skill reads global CSS, theme/token files, font declarations, and icon libraries from a local or remote codebase.
Boundary markers: There are no explicit instructions to use delimiters or ignore instructions that might be embedded within CSS comments or configuration files.
Capability inventory: The skill can read local files and write/update assets within a Framer project via the official framer skill.
Sanitization: While the skill mentions using 'reliable tooling' to resolve CSS expressions, it does not explicitly provide instructions for sanitizing or filtering instructions hidden in the processed data.

sync-styles