apache-spark
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the well-known
pysparklibrary from the official Python Package Index. - [COMMAND_EXECUTION]: Provides instructions for running environment setup and data processing code.
- [PROMPT_INJECTION]: Found indirect prompt injection attack surface. (1) Ingestion points: Data is loaded from Amazon S3 and Kafka topics in
etl/process.pyandSKILL.md. (2) Boundary markers: Absent; there are no delimiters to separate ingested data from agent instructions. (3) Capability inventory: Capabilities include writing transformed data back to S3 buckets. (4) Sanitization: Absent; no validation or filtering is performed on the ingested data content.
Audit Metadata