market-research-automation
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary logic relies on hardcoded mock data and standard reporting structures. No obfuscation, credential theft, or persistence mechanisms were detected.
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install standard Python packages (requests, beautifulsoup4, pandas). These are well-known libraries, though the instructions do not specify version constraints and the current script version does not yet utilize them.
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface (Category 8) by interpolating user-provided command-line arguments into generated Markdown files. 1. Ingestion points:
args.market,args.products, andargs.topicinscripts/market_researcher_tool.py. 2. Boundary markers: None. 3. Capability inventory: File writing (open().write()) inscripts/market_researcher_tool.py. 4. Sanitization: None.
Audit Metadata