data-researcher

Warn

Audited by Snyk on Feb 15, 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 ingests and analyzes untrusted user-generated content — see "Example 3: Social Media Sentiment Analysis" ("Data Collection: Gathered social media mentions, reviews, and news articles") and the "Text Analysis"/"Data Ingestion" sections — so the agent would read and interpret open/public third‑party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:30 PM