dataset-loader-creator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [General Analysis] (SAFE): The skill consists entirely of markdown instructions and metadata. No executable code, obfuscation, hardcoded credentials, or malicious patterns were found.
- [Indirect Prompt Injection] (LOW): The skill is designed to create loaders for external datasets, which introduces a surface for indirect prompt injection. * Ingestion points: External datasets processed by generated loaders; * Boundary markers: None provided in the instructions; * Capability inventory: Access to Read, Write, Edit, and Bash (python/pip) tools; * Sanitization: No sanitization or validation logic is defined for the ingested data.
Audit Metadata