skills/nexscope-ai/nexscope-ecommerce-skills/ecommerce-tiktok-top-selling-products/Gen Agent Trust Hub
ecommerce-tiktok-top-selling-products
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes product data from a remote API (FastMoss TikTok data source), which creates a potential surface for instructions embedded in external data to influence the agent.
- Ingestion points: The
scripts/tiktok_top_selling_products.pyscript fetches data including product titles, shop names, and categories from the remote API endpoint. - Boundary markers: There are no specific instructions or delimiters provided to the agent to treat the retrieved JSON data as untrusted or to ignore embedded instructions within the fields.
- Capability inventory: The skill uses a Python script that has permissions to create directories and write files to the local project environment (under the
nexscope/directory). - Sanitization: The script parses the API response as JSON but does not perform content filtering or sanitization on string fields before they are output to the agent's context.
Audit Metadata