enterprise-ai-scenario-map

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a local Python script scripts/deep_research_wrapper.py to generate search frameworks and query lists. Technical review of the script confirms it is a safe utility that performs string formatting and text output without any network access, file system modifications, or dynamic code execution.
  • [EXTERNAL_DOWNLOADS]: The workflow involves the use of the web-search tool to gather corporate and industry data. This activity is restricted to the primary purpose of researching company profiles and finding relevant AI case studies for report generation.
  • [DATA_EXFILTRATION]: No exfiltration or sensitive data exposure was detected. The skill contains hardcoded contact details (WeChat ID, company name) for the developer (Yuanzi AI), which are used for footer information and contact sections within the generated reports as per standard vendor practice.
  • [PROMPT_INJECTION]: The skill ingests external data from web searches. While it lacks specific boundary markers or delimiters for this data, the agent's capabilities in this context are limited to text synthesis and reporting, and it does not use the ingested data to trigger high-risk tools or shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 03:51 AM