elfa-api
Warn
Audited by Snyk on Mar 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill calls Elfa's public API (see "API Overview" and endpoints like /v2/data/keyword-mentions, /v2/data/top-mentions, /v2/data/trending-narratives in SKILL.md), which ingests user-generated Twitter/X and Telegram content and instructs the agent to parse and act on that data (see "Presenting results"), so untrusted third-party content can materially influence agent decisions.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill explicitly supports x402 "pay-per-request" using USDC on the Base chain. It documents a payment flow that returns HTTP 402, requires the client/wallet to sign an EIP-712 payment authorization, and resend with an X-PAYMENT header. The skill includes concrete code and libraries for signing and sending payments (e.g., privateKeyToAccount("0xYOUR_PRIVATE_KEY"), toClientEvmSigner, wrapFetchWithPayment, @x402/fetch) and specifies chain and token addresses. These are specific crypto payment/signing capabilities (wallet signing and on-chain USDC payments), i.e., direct financial execution functionality.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata