cakebaba-crypto-skill

Warn

Audited by Snyk on Jun 23, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow can fetch public web content from outsider-controlled sources (Binance/CoinGecko HTTP JSON responses) via scripts/fetch_crypto_data.py (e.g., --mode ohlcv/summary/leverage), which is then ingested as readable text/JSON and used to generate the LLM’s analysis—an indirect prompt-injection exposure path.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 23, 2026, 05:06 AM
Issues
1