world-labs-text-prompt
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The skill consists of instructional content and reference tables. No attempts to override agent behavior or bypass safety constraints were detected.
- [Data Exposure] (SAFE): No sensitive credentials, API keys, or private file paths are present. Examples use non-functional placeholders.
- [Remote Code Execution] (SAFE): No commands for downloading or executing remote scripts were found. The skill is entirely declarative markdown.
- [Indirect Prompt Injection] (SAFE): As a static reference guide, the skill does not ingest or process untrusted external data, presenting no surface for indirect injection attacks.
Audit Metadata