fal-upscale

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs fetching/installing the upstream bundle from the public GitHub repo https://github.com/fal-ai-community/skills (a third-party, user-generated source) to run the workflow, meaning the agent would ingest and act on external repo content that could materially change behavior.