referrals
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill consists of marketing documentation and playbooks. It does not contain any executable code, scripts, or instructions that trigger automated command execution or file system access.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted customer reviews and platform metadata. 1. Ingestion points: Text and profiles from external review platforms. 2. Boundary markers: Includes explicit instructions for the agent to treat this data as untrusted and to ignore any instructions embedded in the content. 3. Capability inventory: The skill does not possess capabilities for shell execution, file-writing, or network requests. 4. Sanitization: Instructs the agent to keep sensitive account history and private support records out of public replies.
- [EXTERNAL_DOWNLOADS]: The skill references several external marketing tools (e.g., Rewardful, Stripe, PartnerStack) and provides links to official platform documentation. These references are standard for growth marketing and point to established services or the author's own GitHub repositories.
Audit Metadata