fusion-dependency-review

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly requires fetching and ingesting untrusted, user-generated content (e.g., "fetch existing top-level PR comments and review threads through GitHub MCP" and checking upstream changelogs, issue tracker threads, and security advisories) and uses those sources as core inputs that influence lens assessments, recommendations, and merge-related actions.