orugas-design-studio

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). This is a GitHub repository from an individual account that includes instructions to install and run code locally (npm install, node script) — downloading and executing code from an unvetted personal repo can be used to distribute malware.

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the LLM context via the runtime --prompt argument (user-supplied text) and is then sent to ai.models.generateContent/generateImages as contents/prompt (and optionally rewritten/suggested), so the agent ingests untrusted text authored by someone other than the operating user.