rawugc-api
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data that is subsequently processed by remote AI models, presenting an indirect prompt injection surface.
- Ingestion points: Several fields including
prompt(in generation endpoints),brief(in content plans), andq(in viral search) accept arbitrary natural language input (SKILL.md,reference.md). - Boundary markers: The instructions do not specify any delimiters or instructions for the agent to ignore embedded commands within user-provided strings.
- Capability inventory: The skill performs network operations via API requests to the RawUGC production environment (
https://rawugc.com). - Sanitization: No explicit validation, filtering, or sanitization of user-provided content is documented before it is passed to the API endpoints.
Audit Metadata