splitting-datasets
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill instructions specify that the agent will generate and execute Python code based on user requests to perform data splitting tasks. This runtime generation and execution of code is the primary function of the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data from sources such as CSV datasets, YAML configuration files, and JSON schemas to inform the generation of executable code. 1. Ingestion points: 'assets/example_dataset.csv', 'assets/split_data_config.yaml', and 'assets/dataset_schema.json' as well as user-provided dataset paths. 2. Boundary markers: None identified in the instructions to explicitly delimit untrusted data or ignore embedded instructions. 3. Capability inventory: The skill is granted access to the Bash tool and file manipulation tools (Read, Write, Edit). 4. Sanitization: No explicit sanitization or validation of the input file content is described before it is used to generate logic for executable scripts.
Audit Metadata