product-hunt-launch

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

• Third-party content exposure detected (high risk: 0.80). SKILL.md explicitly instructs running belt app commands like "belt app run tavily/search-assistant" and "belt app run exa/search" to research Product Hunt launches, competitor launches, and community sentiment—these fetch and ingest public web/search results and user-generated community content that the agent is expected to read and that can materially influence launch decisions.

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 at runtime (https://inference.sh) via "belt app run" to execute remote apps (e.g., falai/flux-dev-lora, tavily/search-assistant), which runs external code and drives prompt-based behavior, so this is a runtime external dependency that can control execution.