agent-builder
Warn
Audited by Snyk on Sep 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The workflow includes an always-on agent daemon (
daemon_run.py) and message tool (agent_message) that continuously poll and ingest user and inter-agent messages frominbox.json, allowing outsider-submitted text if the inbox is exposed.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata