figma-to-ai-prompter
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSMETADATA_POISONING
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the Figma API which could contain malicious instructions or structures designed to subvert the AI agent's behavior during prompt generation.
- Ingestion points: Figma design data is fetched via the
fetchFigmaFilefunction and processed inSKILL.md. - Boundary markers: The prompt templates in
SKILL.md(e.g., for Lovable and Figma Make) use simple placeholders like{DESIGN_STRUCTURE}without explicit delimiters or instructions to ignore embedded commands. - Capability inventory: The skill generates complex prompts and code for prototyping tools and includes a validation loop that sends generated output back to an AI model for refinement.
- Sanitization: The transformation scripts in
SKILL.mdperform property extraction and stringification but do not demonstrate sanitization of user-controlled text fields within the Figma design. - [EXTERNAL_DOWNLOADS]: The documentation instructs the user to clone a repository and install dependencies from an external source.
- Evidence:
git clone https://github.com/royvillasana/figma-to-ai-prompter.gitinSKILL.md. - [METADATA_POISONING]: The skill documentation attribute ownership and authorship to
ara.soandRoy Villasana, which differs from the provided vendor context.
Audit Metadata