referral-program
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown content. No code, scripts, or executable commands are present.
- [PROMPT_INJECTION]: No attempts to override system instructions or bypass safety filters were detected. The persona is consistent with a professional marketing expert.
- [DATA_EXFILTRATION]: There are no commands to access sensitive files or perform network requests. References to third-party marketing tools (e.g., ReferralCandy, Stripe) are mentions of services for the user to consider, not active connections.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or credentials were found. Placeholder templates for emails and outreach are safe for general use.
- [OBFUSCATION]: The content is clear text with no encoded strings, zero-width characters, or hidden patterns detected.
- [DYNAMIC_CONTEXT_INJECTION]: The skill does not use shell execution patterns (!
command) in its instructions.
Audit Metadata