cortex-search-tutorial
Warn
Audited by Snyk on Mar 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to perform a runtime web_fetch of the Snowflake documentation (https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-search/cortex-search-overview) and to use that fetched content as the source of truth for prompts/behavior, which means an external URL is fetched at runtime and directly controls agent instructions.
Audit Metadata