csv-data-cleaning
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external CSV and tabular data, creating an attack surface for indirect prompt injection. * Ingestion points: CSV and flat tabular files as described in SKILL.md. * Boundary markers: The instructions lack specific delimiters or instructions for the agent to ignore command-like text within the data fields. * Capability inventory: The skill involves reading, transforming, and writing files. * Sanitization: The cleaning process focuses on data types and formats but does not explicitly address the sanitization of embedded instructions.
Audit Metadata