parsing-changelogs

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent/subagents to fetch and parse public third-party pages and feeds (see "Fetching", "Crawl Mode", and the "Dispatch a bulk-worker subagent" sample prompting "Fetch these URLs with WebFetch..."), so untrusted web content is consumed and can directly influence parsing decisions and subsequent tool actions.