mastra

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs runtime fetching of remote documentation (e.g., https://mastra.ai/llms.txt) and shows WebFetch examples that pull markdown into the agent context to drive API usage and prompts, so the externally fetched content can directly control agent instructions at runtime.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 02:37 AM