deephaven-core-query-writing
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of technical documentation and Python code snippets for the Deephaven library. All external links point to official vendor documentation at deephaven.io.
- [PROMPT_INJECTION]: The skill describes operations for ingesting data from external sources, which is an inherent feature of a data processing library.
- Ingestion points: External data is ingested via functions such as
read_csv,read_parquet,kc.consume(Kafka), andadapter.load_table(Iceberg) as shown in SKILL.md and various reference files. - Boundary markers: The provided code examples do not use specific delimiters or instructions to ignore embedded prompts within the processed data.
- Capability inventory: The skill enables data manipulation, aggregations, and the ability to produce data back to external systems (Kafka, CSV, Parquet).
- Sanitization: No explicit sanitization or validation of external data content is demonstrated in the provided code snippets.
- [CREDENTIALS_UNSAFE]: The skill includes placeholders for credentials in configuration examples for Kafka and Iceberg (e.g.,
s3.access-key-id": "my-access-key"). These are standard placeholders and do not represent hardcoded secrets.
Audit Metadata