finnhub

Warn

Audited by Snyk on Mar 12, 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.md explicitly exposes fetching public third‑party content (e.g., "Get Company News", "Get General News", "Transcripts"/"Transcript Sentiment" and the "Proxy requests" to Finnhub API) via Membrane, so the agent will read untrusted external news/transcript content that can influence its decisions or subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 12, 2026, 12:26 PM
Issues
1