researcher
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and instructional content. No executable scripts, binaries, or automated command patterns were found. The skill includes thorough safety and privacy guidelines for handling research data, including PII anonymization and GDPR compliance requirements.
- [SAFE]: Analysis of the instructions shows no evidence of prompt injection or attempts to bypass safety guardrails. The skill focuses strictly on its defined domain of user research and provides specific boundaries for agent behavior.
- [SAFE]: No sensitive data exposure or exfiltration patterns were detected. Network references are limited to well-known research platforms and internal agent framework documentation.
- [SAFE]: The 'multi-engine' research design mode is a documented orchestration pattern for spawning subagents to provide diverse perspectives, which is consistent with the skill's generative research purpose and does not introduce security vulnerabilities.
Audit Metadata