amz-brand-tailored-promotions
Pass
Audited by Gen Agent Trust Hub on May 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of natural language instructions intended to guide the agent's logic. It does not utilize any platform tools, execute shell commands, or perform file system operations.
- [EXTERNAL_DOWNLOADS]: The skill contains a reference to an external community group on WhatsApp (chat.whatsapp.com). This link is provided for optional user engagement and does not involve automated remote code execution or background data transfers.
- [PROMPT_INJECTION]: The skill is designed to process user-provided parameters such as brand goals and audience metrics. While the instructions do not include explicit boundary markers for this untrusted data, the skill possesses no access to sensitive tools, network utilities, or system commands that could be exploited via indirect prompt injection.
Audit Metadata