figma-reader

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill fetches and reads user-created Figma designs via Figma MCP from Figma links or prompts (see SKILL.md and references/rules.md "Design Input"), which are untrusted third-party content that the agent ingests and uses to produce outputs and drive subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill reads external Figma file URLs at runtime (e.g., https://www.figma.com/design/...), and content fetched from those files—including user-provided "prompts" copied from Figma—will be injected into the agent's context and can directly control the agent's instructions.