skills/nexscope-ai/nexscope-ecommerce-skills/ecommerce-chuhaijiang-tiktok-product/Gen Agent Trust Hub
ecommerce-chuhaijiang-tiktok-product
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API responses which presents a surface for indirect prompt injection.
- Ingestion points: All Python scripts in the scripts/ directory ingest JSON data from api.nexscope.ai.
- Boundary markers: Absent; data is processed and written directly to local files.
- Capability inventory: The scripts are capable of making network requests and writing JSON files to the local nexscope/ directory.
- Sanitization: Scripts include a validate_params function that enforces strict types and formats for request parameters.
- [DATA_EXPOSURE_AND_EXFILTRATION]: Performs network operations to the vendor's API endpoints.
- The scripts communicate with api.nexscope.ai to fetch market intelligence data.
- Authentication is managed through the NEXSCOPE_API_KEY environment variable, following standard security practices for credential management.
Audit Metadata