blogwatcher

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly instructs fetching public RSS feeds and blog-style content with feedparser.parse (see "Parse a Feed" and "Batch Fetch Multiple Feeds") and then feeding entry titles/summaries/links into Claude for synthesis, so the agent consumes untrusted third-party web content that can influence its decisions.