baml

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: 0.80). The examples/usage.py multimodal_examples shows Image.from_url(...) passed into AnalyzeImage, which allows the agent to fetch and interpret arbitrary external images by URL (untrusted third-party content) as part of its workflow, enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 10:10 PM