spark-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external sources, which creates a vulnerability to indirect prompt injection where malicious instructions could be embedded in the processed data.
- Ingestion points: The skill provides code patterns for reading data from S3 buckets (
SKILL.md), Kafka topics, and external files (references/streaming-patterns.md). - Boundary markers: There are no explicit instructions or markers provided to help the agent distinguish between data and potentially malicious instructions within that data.
- Capability inventory: The skill uses distributed processing and performs network operations (S3, Kafka, JDBC), which could be leveraged if the agent were to follow instructions injected into the data stream.
- Sanitization: The provided examples do not demonstrate sanitization or validation of the data content prior to processing or analysis by the agent.
Audit Metadata