fusion-dependency-review

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs fetching existing PR comments and review threads via "GitHub MCP" and gathering upstream changelogs, issue tracker/discussion threads, and security advisories (all untrusted, user-generated or public web content) which the agent is required to read and use to decide whether to merge/hold — enabling indirect prompt injection.