persona-researcher

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and defines a research persona. It contains no executable scripts, hardcoded credentials, or network exfiltration patterns.
  • [SAFE]: The instructions mandate a read-only approach to the codebase, explicitly instructing the agent to 'keep your hands off the codebase' and to verify that no files have been modified using 'git status'.
  • [SAFE]: The focus on verifiable primary sources and the requirement to 'web-verify a source's venue' are standard procedures for a research assistant and do not pose a security risk in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 02:49 PM
Security Audit — agent-trust-hub — persona-researcher