flutter-improve-design

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

• Third-party content exposure detected (low risk: 0.10). The workflow requires fetching an external web page via curl from a URL specified in the catalog (DETAILS.md), which constitutes low-risk outsider-authored content extraction.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs the agent at runtime to fetch and use a remote catalog file (https://raw.githubusercontent.com/kamranbekirovyz/skills/main/flutter-improve-design/DETAILS.md) and external markdown details articles via curl to guide its code review and implementation plan generation.