aave-v2-plugin
Warn
Audited by Snyk on Jun 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The required pre-flight workflow fetches and executes outsider-authored free text/code from public web sources at runtime (e.g.,
curl ... https://raw.githubusercontent.com/.../launcher.shandupdate-checker.pyandcurl .../install.sh), which is then ingested/executed by the agent environment and can influence the LLM context indirectly via generated outputs/logs.
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 install steps fetch and execute remote installer/binaries at runtime (notably the onchainos installer script fetched from https://raw.githubusercontent.com/okx/onchainos-skills/${LATEST_TAG}/install.sh and the plugin binary/checksums from https://github.com/okx/plugin-store/releases/download/plugins/aave-v2-plugin@0.1.1/... ), so external URLs are used at runtime to deliver code that the skill installs/executes.
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 actions. It exposes commands that build, sign (via onchainos), and submit transactions to Aave V2: supply (deposit), withdraw, borrow, repay, claim-rewards, and swap-borrow-rate-mode. The SKILL.md documents specific contract calls (LendingPool.deposit/withdraw/borrow/repay, IncentivesController.claimRewards), approval flows, tx confirmation, and use of an onchainos wallet signer/contract-call flow. Even though some supply/borrow paths are pre-flight-blocked for V2 wind-down, withdraw, repay, claim-rewards, and swap-borrow-rate-mode are functional and can move funds. This is a direct crypto/blockchain execution capability (wallet signing and transaction submission), not a generic tool. 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