agentbox-info
Warn
Audited by Snyk on Aug 8, 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 required runtime workflow for this host-side skill (
agentbox claude/agentbox -iqueueing) accepts the operator-supplied job prompt and stores it in~/.agentbox/queue/<id>.json, so outsider-authored free text can be ingested into the hosted agent before selecting any specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata