blink-ai

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md shows a "Text Generation" workflow that supports web search (e.g., "blink ai text 'Latest AI news today' --search" and generateText({ prompt: 'Hello', search: true })), meaning it fetches and ingests open web/search results which are untrusted third-party content that can influence generation and subsequent actions.