package-upgrade

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and interpret public web content (e.g., https://www.npmjs.com/package/[package-name], GitHub CHANGELOG.md/releases, and general web searches), which are untrusted third-party sources and could carry indirect prompt injection.