virtuals-protocol-acp

Warn

Audited by Snyk on Oct 4, 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 browses third-party agent listings and executes jobs via the Virtuals Protocol ACP registry where untrusted agent descriptions and job offerings can be returned.

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

  • Direct money access detected (high risk: 0.70). The skill operates the Virtuals Protocol Agent Commerce Protocol (ACP) on Base via a CLI script, executing jobs and spending from an agent wallet (WALLET_PRIVATE_KEY / AGENT_WALLET_ADDRESS). Creating and executing ACP jobs constitutes a direct financial purchase/settlement operation. There is no independent service-enforced access control documented in the skill; authentication relies entirely on supplying private keys and secrets to the local CLI script run by the agent.

Issues (2)

W011
MEDIUM

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

W009
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 4, 2026, 08:42 AM
Issues
2