weather-live
Warn
Audited by Snyk on Aug 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The runtime workflow only ingests outsider-authored free text that the caller provides as the
--searchquery or askey=valuearguments to a chosen catalog service; it does not automatically read arbitrary external feeds or messages without the agent first selecting a specific item (service-id/parameters).
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill explicitly requires and documents on-chain/off-chain crypto payments: it asks for a spending wallet private key in FITTINGS_PRIVATE_KEY, specifies USDC on Base, describes an off-chain signature authorizing a USDC transfer and that the facilitator submits the transaction, and gives an example export of the private key. These are specific wallet/crypto payment instructions that enable the agent to sign and authorize transfers (direct financial execution).
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata