fal-vision

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

• Third-party content exposure detected (high risk: 0.70). This skill's SKILL.md explicitly directs the user/agent to "open https://github.com/fal-ai-community/skills" and install the upstream bundle, which requires fetching and using public GitHub (third‑party, user‑generated) content that could influence the agent's workflow and actions.