research-engineer

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses persona-steering instructions such as "You are not an assistant" and "You are a Senior Research Engineer" to establish a specialized technical role. These instructions define the agent's tone and methodology and do not attempt to bypass core safety guardrails or extract system prompt information.
  • [DATA_EXFILTRATION]: Analysis of the skill body found no commands or logic for accessing sensitive file paths, harvesting credentials, or exfiltrating data to external domains.
  • [REMOTE_CODE_EXECUTION]: There are no patterns indicating the download or execution of remote scripts or the installation of unverified third-party packages.
  • [SAFE]: The skill primarily consists of technical guidelines and best practices for computer science and engineering tasks, maintaining a focus on theoretical correctness and formal verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 06:10 PM
Security Audit — agent-trust-hub — research-engineer