hook-3s-script
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a prompt template that incorporates untrusted user input (product descriptions and selling points) directly into the agent's instructions. This creates a surface where malicious instructions hidden in the product data could potentially influence the agent's behavior.
- Ingestion points: User-supplied strings for placeholders such as
{商品名},{谁，在什么时候用}, and{卖点}inSKILL.md. - Boundary markers: The template does not utilize delimiters or specific instructions to ignore embedded commands within the input variables.
- Capability inventory: The skill is designed for text generation and structured data (JSON) output for video scripts.
- Sanitization: No sanitization or validation of the input fields is implemented.
- [SAFE]: The skill contains a reference to a GitHub repository (
github.com/xianyu110/ecommerce-video-skills) which belongs to the skill's author. This is a standard resource reference and does not involve dynamic code execution or data exfiltration.
Audit Metadata