dev-figma-capture
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches a JavaScript capture script from Figma's official domain (mcp.figma.com). This is a legitimate operation used to facilitate the conversion of HTML to Figma design data.\n- [COMMAND_EXECUTION]: Utilizes the open command to navigate to URLs and node to execute the local capture script. These actions are standard for the skill's intended purpose of web automation.\n- [DATA_EXFILTRATION]: Sends the processed web content to Figma's capture submission endpoint. This is the core functionality of the skill and targets a well-known service provider.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes content from user-specified URLs.\n
- Ingestion points: Data enters the context via the URL provided by the user in SKILL.md and through the browser navigation in figma-capture.mjs.\n
- Boundary markers: None identified; there are no specific delimiters used to isolate user-provided data or web content from instructions.\n
- Capability inventory: Subprocess execution for browser control and interaction with Figma's MCP tools for design generation.\n
- Sanitization: No content filtering or protocol validation is applied to the input URLs or the captured DOM.
Audit Metadata