provider-upgrade

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to search GitHub issues and registry upgrade guides (diagnostic-toolbox.md), which constitutes low-risk outsider-authored content fetching.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references an external release URL on GitHub to fetch and execute schema-tools during runtime, which introduces a common/reputable unofficial operational dependency.