alterlab-genai-text-to-image

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly directs the agent to "Search the web for current Higgsfield models, new model releases, prompt syntax updates, and pricing changes" (SKILL.md, Workflow step 1), meaning it fetches and reads untrusted public web content that can influence model selection and prompt actions.