ito-data-atlas-agent

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely instructional and provides a framework for workflow planning without including any executable code, shell commands, or automated scripts.
  • [DATA_EXFILTRATION]: The instructions mention the requirement for an ITO_API_KEY for read-only access in future implementations. This is framed as a security guardrail to limit access and does not involve the harvesting or hardcoding of credentials.
  • [PROMPT_INJECTION]: The proposed architecture identifies the risk of prompt injection when ingesting data from external sources and explicitly includes a 'Risk reviewer' role to audit for such exposure.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:47 PM
Security Audit — agent-trust-hub — ito-data-atlas-agent