ai-daily

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

• Third-party content exposure detected (high risk: 0.90). This skill directly fetches and parses an open/public RSS feed at https://news.smol.ai/rss.xml (see scripts/fetch_news.py) and then consumes the feed entries' content as markdown/html input (used in output templates and theme prompts), meaning the agent reads and interprets untrusted third‑party website content as part of its workflow.