research-engineer

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of markdown instructions defining a Research Engineer persona for data gathering and technology analysis. It does not contain any executable scripts, obfuscated content, or hardcoded secrets.
  • [COMMAND_EXECUTION]: The skill references standard tools such as grep_search, find_by_name, and view_file for codebase analysis. These are used in accordance with the skill's stated purpose and do not involve arbitrary or malicious command execution.
  • [PROMPT_INJECTION]: No evidence of prompt injection, instructions to bypass safety guidelines, or attempts to extract system prompts was found.
  • [EXTERNAL_DOWNLOADS]: The skill mentions a search_web tool for external information gathering. This is a common capability for research agents and does not point to specific untrusted domains or unauthorized data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 07:19 PM