rowlab
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from datasets that are subsequently used in prompts for AI models.
- Ingestion points: Data enters the context via
dataset_add,dataset_get, andsql_queryinSKILL.md. - Boundary markers: The instructions recommend using
run_previewto inspect the generated prompt, providing a point for manual verification, though no programmatic boundaries are enforced. - Capability inventory: The agent can perform SQL queries, trigger LLM-based labeling (
run_start), and export data (dataset_export). - Sanitization: There are no specific instructions to sanitize or escape the content of the dataset rows before they are interpolated into the prompt templates.
Audit Metadata