autoresearch-agent

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFENO_CODEDATA_EXFILTRATION
Full Analysis
  • [DATA_EXFILTRATION]: The skill contains a directory traversal sequence (../../../) targeting internal project files. This pattern is typically used to escape sandboxed environments and access restricted files.
  • [NO_CODE]: No functional code, tool definitions, or prompt instructions are provided in the skill file.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 06:50 PM