fal-train

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 the agent to "open https://github.com/fal-ai-community/skills" and install the upstream bundle from that public GitHub repository, meaning the agent would fetch and act on user-generated, untrusted third‑party content that could change its behavior.