superdesign

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill mandates automatically collecting and uploading complete UI source files (including full component/layout/theme code and brand assets) to an external SuperDesign service and auto-installing/running a remote CLI — behavior consistent with intentional data exfiltration and supply-chain/RCE vectors.

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

• Third-party content exposure detected (high risk: 0.85). High chance: the workflow fetches outsider-authored free-text from public URLs at runtime (raw.githubusercontent.com INIT.md and SUPERDESIGN.md), which is then used to drive repository scanning instructions and contextual reads for subsequent LLM calls.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires fetching and following remote prompt/instruction files at runtime from https://raw.githubusercontent.com/superdesigndev/superdesign-skill/main/skills/superdesign/INIT.md and https://raw.githubusercontent.com/superdesigndev/superdesign-skill/main/skills/superdesign/SUPERDESIGN.md, which directly control agent behavior and are required for operation.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.50). The skill instructs the agent to automatically create files/directories and fetch & execute remote init instructions, and to install a global CLI (npm install -g) and perform login — actions that modify the host environment and could require elevated privileges or cause unexpected changes if done automatically.