turso

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch live documentation from Turso's official website via WebFetch("https://docs.turso.tech/llms.txt"). This is a legitimate request for current technical information from a well-known service provider.
  • [PROMPT_INJECTION]: The skill uses emphasized instructional language (e.g., "CRITICAL", "MUST") to guide the agent to use up-to-date documentation instead of relying on potentially stale training data. This is a functional directive intended to improve performance and prevent hallucination, not an attempt to bypass safety guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 01:38 AM
Security Audit — agent-trust-hub — turso