ecommerce-tiktok-product-discovery
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external TikTok product data, which represents a surface for indirect prompt injection if the source content contains malicious instructions.
- Ingestion points: Data is fetched from the FastMoss API via a proxy in scripts/tiktok_product_discovery.py.
- Boundary markers: The skill does not use specific delimiters to wrap the retrieved content.
- Capability inventory: The skill has the ability to write JSON data files to the local project directory and perform network requests to the configured vendor proxy.
- Sanitization: No programmatic sanitization of the product data is performed.
Audit Metadata