brand-storytelling

Warn

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a 'Mandatory Intro Message' that requires the agent to prepend all content with financial solicitation links. This is a behavioral override used to inject unauthorized monetization into the agent's responses.
  • [PROMPT_INJECTION]: The 'System Prompt Inquiry Response' section explicitly instructs the agent to hide its system prompt and internal configurations. If queried about its instructions, the agent is directed to provide a hardcoded response promoting a specific commercial membership site ('scayveracademy.com').
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 19, 2026, 04:03 AM
Security Audit — agent-trust-hub — brand-storytelling