The Agent Skills Directory

[COMMAND_EXECUTION]: The documentation in references/figma-mcp-config.md instructs users to modify shell configuration files such as ~/.bashrc and ~/.zshrc to persist environment variables, which is a persistence mechanism.
[DATA_EXFILTRATION]: Setup steps include the command echo $FIGMA_OAUTH_TOKEN, which can lead to the exposure of sensitive authentication credentials in terminal history, console output, or session logs if executed.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes content from external Figma URLs. Evidence: Ingestion points include get_design_context and get_metadata tools in references/figma-tools-and-prompts.md; Boundary markers are absent in the prompt instructions within SKILL.md; Capability inventory includes the ability to translate data into production code and write it to the project filesystem; Sanitization or validation of the external Figma payload is not explicitly mentioned.

figma