strategy-auto-rebalance

Fail

Audited by Snyk on Mar 16, 2026

Risk Level: CRITICAL
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt instructs embedding secrets (EVM_PRIVATE_KEY, TELEGRAM_BOT_TOKEN/--telegram-token) into environment variables or CLI arguments and to verify wallet derived from the private key, which requires handling or emitting secret values verbatim and poses an exfiltration risk.

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.90). The URL is a direct raw GitHub link to an install.sh script from an individual/unknown account and is intended to be piped into a shell (curl | sh), which is high-risk because it can execute arbitrary code on the machine without vetting.

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests external public data (Morpho GraphQL vault discovery and DeFiLlama fallback API) and uses those untrusted third-party sources to compute yields/TVL and make automated rebalance decisions, so remote content can materially influence tool actions.

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). The skill is explicitly a daemon that monitors yields and executes on-chain transactions to move USDC between Aave V3, Compound V3, and Morpho. It requires an EVM_PRIVATE_KEY, describes execution steps ("approve + withdraw + verify wallet balance + deposit + verify target balance"), auto-deposit of idle USDC, emergency withdrawal, and CLI commands to "start" the auto-rebalance daemon that will perform rebalances. These are specific payment/asset-moving capabilities (blockchain wallet signing and transaction execution), not generic tooling, so it grants direct financial execution authority.

Issues (5)

W007
HIGH

Insecure credential handling detected in skill instructions.

E005
CRITICAL

Suspicious download URL detected in skill instructions.

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
CRITICAL
Analyzed
Mar 16, 2026, 06:44 PM
Issues
5