oneshot-messaging
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 skill workflow monitors and reads incoming SMS messages via
agent.smsInboxList, allowing any external sender to inject untrusted free text into the agent's runtime.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 0.70). The skill operates SMS and autonomous voice call functionalities via the OneShot SDK, explicitly stating they are "paid in USDC via x402" and may include phone registration and usage fees. This constitutes a direct payment/purchase operation (paying for communication services). Although wallet setup and authentication are mentioned as handled via the
oneshotskill, the provided text does not contain documentation of independent access control enforced by the service or execution layer for the routes in this file (other than client SDK initialization and passing parameters likemaxCost). Therefore, it falls under direct operations without established qualifying independent control.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata