snowflake-expert
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill provides patterns for processing data from external cloud storage and internal streams, establishing a surface for indirect prompt injection.
- Ingestion points: The
SKILL.mdfile contains SQL templates forCREATE EXTERNAL TABLEandCOPY INTO, which enable the agent to read data from external S3 and Azure Blob Storage locations. - Boundary markers: Absent. The provided SQL snippets do not include instructions or delimiters to help the agent distinguish between trusted instructions and untrusted data from these external sources.
- Capability inventory: The skill is configured with access to powerful tools including
Bash,Write, andEditin its frontmatter. - Sanitization: Absent. The examples focus on data platform functionality and do not demonstrate validation or escaping techniques for ingested content.
- [SAFE]: The skill uses safe placeholders such as 'xxx' and 'yyy' for sensitive credentials in its Snowflake configuration examples.
- [SAFE]: The dependency
snowflake-connector-pythonis an official and well-known library for Snowflake integration.
Audit Metadata