figma-bridge

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime path can ingest outsider-authored free text from Figma via get_design_context / get_variable_defs / get_libraries when the user supplies a Figma file/node URL for design-review or design-system extraction, and those tools return readable node text/metadata into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill mandates loading external Figma usage guidance at runtime (invoke /figma-use or read the skill://figma/figma-use/SKILL.md MCP resource), which directly controls how the agent performs Figma writes and thus influences its instructions.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)