dependency-upgrade

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

• Third-party content exposure detected (low risk: 0.10). The skill contains instructions to fetch and read external changelogs or codemods via curl or web-based URLs, which constitutes fetching outsider-authored text at runtime.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill references raw GitHub URLs to retrieve changelogs and codemods during execution, but these GitHub URLs lack strong first-party verification and fall into the weak/unknown/suspicious operational dependency category.