raydium-plugin

Warn

Audited by Snyk on Apr 28, 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). This skill directly fetches and consumes live data and transaction responses from public Raydium endpoints (e.g., https://api-v3.raydium.io and https://transaction-v1.raydium.io via get-swap-quote, get-token-price, get-pools and swap flows described in SKILL.md and implemented in the command code), and those untrusted third‑party responses are read by the agent and used to make decisions and build/broadcast transactions, so they can materially influence tool use.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).


MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). This skill is explicitly designed to perform on-chain token swaps on Solana. It includes wallet login/address resolution, balance checks, a get-swap-quote flow and a swap command that "builds the transaction and broadcasts it" via onchainos (uses wallet contract-call with --unsigned-tx --force). It returns tx hashes and enforces pre-flight checks and confirmations, but still performs actual signed transactions and moves crypto. These are concrete crypto/blockchain transaction and signing capabilities (wallet integration + swap execution), which meet the "Direct Financial Execution" criteria.

Issues (3)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 28, 2026, 10:45 AM
Issues
3