ecommerce-tiktok-product-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute Python scripts (
scripts/product_rank.pyandscripts/product_detail.py) via the command line to fetch and process data from the TikTok API. This is the primary intended functionality. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external TikTok product leaderboards, creating a theoretical surface for indirect prompt injection if product titles or descriptions contain malicious instructions.
- Ingestion points: External data enters the agent context via API responses fetched by the Python scripts in the
scripts/directory. - Boundary markers: Absent. The skill instructions do not explicitly provide delimiters or warnings to the agent to disregard instructions potentially embedded in the fetched product data.
- Capability inventory: The skill has the capability to execute shell commands (running the scripts), perform network requests to the NexScope proxy, and write files to the local filesystem.
- Sanitization: No specific sanitization or escaping of the remote API content is performed before the data is displayed or saved.
Audit Metadata