inbox
Warn
Audited by Snyk on Feb 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly reads messages published by other agents/sessions from the inbox topic (agent..inbox) via commands like "hive msg inbox", which ingests untrusted, user-generated inter-agent content that can directly influence agent actions.
Audit Metadata