oneshot-email
Warn
Audited by Snyk on Nov 1, 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 agent reads inbound emails via the OneShot SDK inbox methods, exposing it to outsider-authored email bodies and content.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 0.70). The skill performs email sending operations paid per-send in USDC via x402 and provisions domains (~$10 one-time), constituting a direct financial operation (purchases/charges). The operations are executed via the OneShot SDK (
@oneshot-agent/sdk), which requires wallet setup and client initialization (OneShot.create({ cdp: true })), but no independent authentication or authorization check is enforced by the service layer over the SDK route itself documented within this skill (only client-side method calls and idempotency keys).
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata