ai-assisted-prototyping

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The documentation is largely benign product-prototyping guidance, but it explicitly includes examples/templates that facilitate deliberate abusive behavior (e.g., "paywall bypass" and tools to download content), which indicates intentional misuse potential.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md:5 and SKILL.md:54-55 indicate the skill uses “insights from 15 guests” and references stored in references/guest-insights.md, which contains outsider-authored free text (guest quotes and tactical advice) that would be ingested into the agent’s LLM context at runtime.