batch-product-research
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to automate keyword research and report generation using specialized sub-agents.
- [DATA_EXFILTRATION]: The skill processes user-provided keywords and generates local report files. It does not access sensitive user credentials, environment variables, or private system files.
- [COMMAND_EXECUTION]: No evidence of arbitrary shell command execution or unauthorized system access was found.
- [PROMPT_INJECTION]: The skill provides instructions for sub-agents and processes user keywords.
- Ingestion points: User-provided keywords are parsed from input and passed to tool calls and reports.
- Boundary markers: No explicit boundary markers or 'ignore' instructions are used for the keywords.
- Capability inventory: The skill uses sub-agent spawning, MCP tool calls (research_products, amazon_keyword_research), and local file writing.
- Sanitization: No keyword sanitization is performed before HTML report generation, which theoretically permits data poisoning (e.g., HTML/JS injection in the generated report).
Audit Metadata