feature-engineering

Warn

Audited by Snyk on Mar 21, 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's build_features.py includes a --live mode that calls fetch_birdeye_ohlcv which fetches OHLCV from the public Birdeye API (https://public-api.birdeye.so), and the SKILL.md also lists birdeye-api and helius-api integrations, so the agent ingests external, public third-party market/on-chain data that directly drives feature computation and downstream decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 21, 2026, 02:35 PM
Issues
1