grpc

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill's "Documentation Resources" section explicitly instructs the agent to fetch external website documentation via Context7 (e.g., "Fetch latest gRPC documentation with Context7" and "Prefer website documentation (IDs starting with '/websites/')"), which requires ingesting open/public web content.

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

  • Direct money access detected (high risk: 1.00). The skill explicitly references "wallet signing operations" and includes proto artifacts like Protos/wallet_service.proto and a WalletService base, indicating native support for crypto wallet signing functionality. That is a specific crypto/blockchain capability (signing transactions), which qualifies as Direct Financial Execution authority under the rules.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 10:17 PM