diffity-resolve-tree

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads user-generated code-review comments from the diffity tree browser via the diffity agent list --status open --json output (the JSON comment bodies) and then interprets those comments to decide and perform code changes and resolve threads, which exposes the agent to untrusted third-party content.