agentcash-wallet

Warn

Audited by Snyk on Oct 24, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). The workflow enables fetching arbitrary API endpoints and searching third-party services via agentcash.fetch and agentcash.search, ingesting outsider-authored content from selected URLs and search results at runtime.

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

  • Potentially malicious external URL detected (high risk: 0.70). The skill instructs the execution of an external package installation via npx (npx agentcash@latest install --client claude-code -y), which constitutes a weak/unknown/suspicious operational dependency fetch at runtime.

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

  • Direct money access detected (high risk: 0.70). The skill operates a direct financial workflow (agentcash.fetch and wallet deposit management) that makes paid API requests by automatically signing and transferring USDC on Base or Solana. There is no independent service or execution-layer access control on these payment requests; the agent directly controls and signs the payment via local wallet keys stored on disk without secondary authentication.

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
Oct 24, 2026, 01:46 PM
Issues
3