research
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Indirect Prompt Injection] (INFO): The skill is designed to fetch and process arbitrary web content, which creates an inherent attack surface for indirect prompt injection. However, the instructions provide robust mitigations by requiring multi-source validation, source quality scoring (Phase 4), and conflict resolution. Because the skill's capabilities are limited to information synthesis and reporting, there is no risk of system-level compromise or side effects.
- [Data Exposure & Exfiltration] (INFO): The skill performs network operations via WebSearch and WebFetch tools. These are legitimate functions for a research tool. No sensitive file paths, environment variable access, or hardcoded credentials were found.
Audit Metadata