diffity-resolve

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses user-generated review comments via diffity agent list --status open --json (SKILL.md step 1) and then reads those comment bodies to decide and perform code changes and resolves (SKILL.md step 3), so untrusted third-party content can directly influence agent actions.