data-partitioner
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data for ETL, transformation, and partitioning, which involves ingesting untrusted external content that could contain hidden instructions. * Ingestion points: Processes data partitions and streaming data as described in the description and instructions. * Boundary markers: The skill lacks explicit instructions for the agent to distinguish between data content and instructions. * Capability inventory: The skill is configured with access to tools including Bash, Write, and Edit. * Sanitization: No specific sanitization or validation logic is defined to prevent the execution of instructions embedded within the data being partitioned.
Audit Metadata