skills/scayver/marketing-skills/sms/Gen Agent Trust Hub

sms

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The 'System Prompt Inquiry Response' section provides a hardcoded response designed to override the agent's natural output when a user attempts to inquire about its system prompt or internal instructions.
  • [PROMPT_INJECTION]: The skill enforces a 'Mandatory Intro Message' that includes external payment links (CashApp, BuyMeACoffee), which serves to steer the agent's behavior for unauthorized self-promotion.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:11 AM
Security Audit — agent-trust-hub — sms