product-hunt-launch

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs using third-party search apps (e.g., infsh app run tavily/search-assistant and exa/search) to research Product Hunt launches and community sentiment, which fetches and feeds untrusted public web/user-generated content that the agent is expected to read and use to guide launch decisions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires the inference.sh CLI and runs remote apps via its service (e.g., infsh app run ...), so the external runtime dependency https://inference.sh is used to execute remote code and handle prompts at runtime (e.g., falai/flux-dev-lora, tavily/search-assistant), making it a required external controller of execution.