viral_content_creator
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The instructions define a marketing persona named 'Echo'. There are no directives to bypass safety filters or ignore system instructions.- [Data Exposure & Exfiltration] (SAFE): The skill contains no file access commands or network requests. It does not handle sensitive user data or hardcoded credentials.- [Remote Code Execution] (SAFE): No scripts, package managers, or remote download commands are present.- [Indirect Prompt Injection] (INFO): The skill takes user input to generate viral copy. While this is an ingestion point for untrusted data, the skill has no dangerous capabilities (like shell access or file writing) to exploit, limiting the risk to purely content-based manipulation within the current chat context.
Audit Metadata