fal-restore

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md "How to use" explicitly tells the agent to "open https://github.com/fal-ai-community/skills" and to install the upstream bundle from that public GitHub repo, which requires the agent to read and act on untrusted, user-generated third-party content that can materially alter its workflow and actions.