landing-page-design

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md Quick Start explicitly runs infsh apps that research competitor landing pages and web search (e.g., "infsh app run tavily/search-assistant" to "Research competitor landing pages" and "infsh app run exa/answer" for social-proof stats), which fetch and have the agent read public, untrusted web content that can materially influence design decisions and tool actions, enabling indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires and invokes the inference.sh CLI (https://inference.sh) at runtime (e.g., multiple "infsh app run ..." and "npx skills add inference-sh/..." commands), which executes remote apps/models and accepts/uses prompts you pass—so external content is fetched/executed and directly controls agent behavior.