exasol-cloud-storage-extension
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides configuration guidance and SQL templates for the Exasol Cloud Storage Extension. All external references point to official vendor documentation and repositories on GitHub, which is a well-known service. The skill follows security best practices by instructing users to utilize Exasol connection objects for credential management rather than hardcoding secrets, and it consistently uses placeholders for sensitive information like access keys and endpoints.
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow for importing data from external sources (S3, GCS, Azure) which represents an attack surface for indirect prompt injection. * Ingestion points: Data is imported from external storage via the BUCKET_PATH parameter in references/cloud-storage-extension.md using UDF scripts. * Boundary markers: No explicit delimiters or instructions to ignore commands within the data are provided in the skill instructions. * Capability inventory: The capability includes database table population and SQL execution within the Exasol environment. * Sanitization: Standard structured file processing (Parquet, Avro, ORC) is used, but no specific content-level sanitization is documented within the skill itself.
Audit Metadata