helius-jupiter

Warn

Audited by Snyk on May 15, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to fetch and use third‑party token metadata and off‑chain content (e.g., "Includes off‑chain metadata (Arweave, IPFS)" in references/helius-das.md) and SKILL.md/integration-patterns require using DAS and Jupiter token/price APIs to build token selectors, enrich metadata, and drive swap/transaction decisions—so the agent will ingest untrusted, user‑generated content from public sources that can materially influence actions.

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

  • Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs loading and executing third‑party JavaScript at runtime via the swap widget script URL https://plugin.jup.ag/plugin-v1.js, which causes remote code to run in the app and is presented as a required dependency for the Jupiter Plugin swap widget.

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

  • Direct money access detected (high risk: 1.00). The skill is explicitly designed to perform on-chain financial operations. It references Jupiter Swap APIs (token swaps and /execute calls), Jupiter Trigger/Recurring APIs (limit orders, DCA, order management), Jupiter Lend write SDKs (deposit/withdraw/borrow), Perps (open long/short positions), and Helius Sender for direct transaction submission (with explicit rules: skipPreflight, fee tips, use of getPriorityFeeEstimate). It instructs how to build and submit trades, recurring buys, limit orders, lend/borrow transactions, and optimized transaction submission—all of which move crypto assets on Solana. These are specific crypto financial execution capabilities (wallet/transaction submission, swaps, order placement), so this skill grants direct financial execution authority.

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
May 15, 2026, 02:47 AM
Issues
3