morpho-plugin
Warn
Audited by Snyk on May 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly fetches runtime data from public third‑party endpoints (e.g., queries to https://blue-api.morpho.org/graphql for MarketParams/positions and GET https://api.merkl.xyz/v4/claim?... for claimable rewards) and the plugin uses those responses to compute health factors, resolve calldata, and drive previews/transactions, so untrusted external content can materially influence actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's pre-flight setup fetches and runs remote installer code (notably https://raw.githubusercontent.com/okx/onchainos-skills/${LATEST_TAG}/install.sh which is downloaded and executed at runtime, and it also pulls launcher and binaries from https://raw.githubusercontent.com/okx/plugin-store/main/scripts/launcher.sh and https://github.com/okx/plugin-store/releases/download/...), so external content is fetched during runtime and executes as a required dependency.
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 financial operations. It provides commands to deposit/supply, withdraw, borrow, repay, supply/withdraw collateral, and claim rewards on the Morpho protocol — all of which construct and submit blockchain transactions. It explicitly uses onchainos wallet contract-call (including forced ERC-20 approve broadcasts) to sign and broadcast transactions and returns tx hashes. These are crypto/blockchain wallet and transaction signing capabilities (directly moving funds), not generic tooling. Therefore it grants Direct Financial Execution Authority.
Issues (3)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata