spark-engineer
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to handle large-scale data processing from external sources such as Amazon S3, Kafka, and relational databases through Spark SQL and DataFrame APIs. This architectural pattern introduces a surface for indirect prompt injection where malicious instructions could be embedded in the data processed by the agent.
- Ingestion points: Data is ingested from S3 buckets (e.g.,
s3://bucket/events/inSKILL.md), Kafka topics (e.g.,references/streaming-patterns.md), and JDBC sources (e.g.,references/streaming-patterns.md). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing these external data sources.
- Capability inventory: The skill documents capabilities for external storage access (S3), network-based data ingestion (Kafka, JDBC), and local file operations, which could be leveraged if an injection is successful.
- Sanitization: While the skill teaches standard Spark transformations, it does not provide specific patterns for sanitizing or validating ingested data against adversarial prompt content.
Audit Metadata