fal-text-to-image

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

• Third-party content exposure detected (high risk: 0.80). The skill accepts a reference image via the CLI "-i, --image Path or URL" (documented in SKILL.md and README) and uses that external image for style-transfer, which means it fetches and processes arbitrary untrusted public image URLs as part of its workflow.