baoyu-translate

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly accepts and fetches arbitrary URLs (see references/workflow-mechanics.md "URL | Fetch content, save to translate/{slug}.md" and SKILL.md Usage ": File path, URL, or inline text"), then analyzes that fetched content and inlines it into prompts/02-prompt.md and spawns subagents to translate chunks, meaning untrusted public webpages could materially influence agent behavior and enable indirect prompt injection.