The Agent Skills Directory

[PROMPT_INJECTION]: The instructions do not contain any patterns intended to bypass safety filters or override the agent's core instructions. The defined operating role is strictly bounded to design-to-code mapping tasks.
[DATA_EXPOSURE_AND_EXFILTRATION]: No hardcoded secrets, sensitive file paths, or network exfiltration patterns were detected. The skill focuses on processing design metadata within the local session context.
[REMOTE_CODE_EXECUTION]: There are no commands or instructions for downloading, installing, or executing external scripts or binaries. The workflow is restricted to generating text-based mapping plans and configuration drafts.
[OBFUSCATION]: The content is presented in clear, readable Markdown. No Base64, hex encoding, zero-width characters, or other obfuscation techniques were found.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from Figma design files (such as layer names, comments, and variables). However, the attack surface is mitigated because the skill lacks dangerous capabilities such as shell access or network connectivity, and its output is intended for developer review before implementation.
[COMMAND_EXECUTION]: The skill does not invoke any shell commands or system utilities. Execution is limited to internal Figma environment actions described as scoped and reversible.

code-connect-mapper