text-splitter
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFE
Full Analysis
- [No Code] (SAFE): The skill consists exclusively of markdown instructions and does not include any executable scripts or tool implementations.
- [Prompt Injection] (SAFE): No patterns of prompt injection, instruction overrides, or safety filter bypasses were identified.
- [Data Exposure & Exfiltration] (SAFE): The skill does not utilize network requests or file system access, and no hardcoded credentials were found.
- [Indirect Prompt Injection] (SAFE): The skill ingests untrusted text data (ingestion point: SKILL.md). However, because the skill defines no executable tools or high-privilege capabilities (capability inventory: none), the injection surface is not exploitable. No boundary markers or sanitization are present.
Audit Metadata