thread-management

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly requires ingesting and parsing inbound email bodies and headers (see "Thread reconstruction", "Quoted reply detection and stripping", and "Thread context for AI agents"), meaning untrusted, user-generated email content is read and fed to AI agents where it can influence decisions and actions.