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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata