quote

Warn

Audited by Snyk on Mar 2, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly performs WebFetch calls to public third‑party APIs (e.g., the KyberSwap Token API and honeypot/FOT API, the aggregator-api.kyberswap.com routes endpoint, and CoinGecko as a fallback) as required workflow steps and uses those JSON responses to determine token addresses, route selection, quoted amounts, and safety warnings, so external content can materially influence agent decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 2, 2026, 04:08 PM