data-transformer
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process datasets, creating a surface for indirect prompt injection where malicious instructions embedded in data could influence the agent. 1. Ingestion points: User-supplied datasets (SKILL.md). 2. Boundary markers: Absent. The instructions do not specify delimiters for data vs instructions. 3. Capability inventory: Generates and potentially executes Python, Pandas, and Spark code for data manipulation. 4. Sanitization: Absent. There are no instructions for the agent to sanitize or validate the content of the datasets against prompt injection.
Audit Metadata