better-auth

Warn

Audited by Snyk on Mar 3, 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 requires loading "exact upstream docs in references/upstream/" as part of the required workflow and documents a refresh command (python3 scripts/fetch_better_auth_llms.py) that fetches upstream public documentation, meaning the agent ingests third‑party public docs that can influence decisions and tool use.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 02:27 PM