market-top-detector

Warn

Audited by Snyk on Feb 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: 0.90). The skill explicitly instructs fetching and ingesting public web data (Phase 1 WebSearch in SKILL.md) and auto-fetches a public TraderMonty GitHub Pages CSV (scripts/breadth_csv_client.py) plus FMP API quotes (scripts/fmp_client.py); those untrusted third-party sources are parsed and directly influence scoring and recommended actions, so they could enable indirect prompt-injection via manipulated external content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 03:07 PM