product-hunt-launch

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow includes fetching “official PH documentation” and “Lenny’s Newsletter” via tools like tavily/search-assistant and exa/search, which can ingest outsider-authored free text from public web pages into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill includes runtime commands that call the inference.sh CLI (infsh) to run remote apps (e.g., "infsh app run falai/flux-dev-lora" / "infsh app run infsh/stitch-images") and points to the installer at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md, showing a required runtime dependency that executes remote code via external services.