fusion-issue-solving

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly requires an issue URL and instructs the agent to "Read the issue body, labels, and linked discussions" on GitHub (public, user-generated content) and to base implementation/PR actions on that content, which exposes the agent to untrusted third-party content that could contain embedded instructions.