fusion-issue-authoring

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly reads and acts on repository-owned, user-generated GitHub content as part of its required workflow—e.g., resolving repository templates (.github/ISSUE_TEMPLATE/) in Step 2 and running duplicate checks with mcp_github::search_issues / GraphQL fallback queries (assets/graphql/*.graphql and references/mcp-server.md) per SKILL.md—so untrusted third-party issue/template content can influence drafting and subsequent MCP mutations.