referral-program

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown documentation and instructional guidelines. No executable scripts, command-line operations, or network requests were identified.
  • [SAFE]: No patterns of prompt injection, data exfiltration, or obfuscation were detected. The skill focuses on marketing strategy and program design advice.
  • [SAFE]: References to external tools (e.g., Rewardful, Stripe) and services are strictly informational and do not involve automated installation, API interaction, or execution of remote code.
  • [SAFE]: While the skill instructions prompt the agent to read context files like '.agents/product-marketing-context.md', the lack of any executable capabilities or network outbound actions mitigates risks associated with indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 11:29 PM