work

Warn

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: MEDIUMDATA_EXFILTRATION
Full Analysis
  • [DATA_EXFILTRATION]: Path traversal pattern detected in SKILL.md (../../../.agents/workflows/work.md). This indicates an attempt to access internal agent files (workflows) located outside the restricted skill directory, which can result in unauthorized data exposure.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 14, 2026, 11:38 PM
Security Audit — agent-trust-hub — work