skills/iii-hq/iii/iii-state/Gen Agent Trust Hub

iii-state

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill serves as architectural documentation for a core platform service (iii-state). It describes legitimate data management operations including storage, retrieval, and reactive triggers.
  • [NO_CODE]: The provided SKILL.md file contains markdown documentation and usage examples but does not include any executable scripts or binary files.
  • [DATA_EXFILTRATION]: The documentation mentions 'redis' and 'bridge' adapters that facilitate network communication. These are documented as standard vendor-provided persistence mechanisms for connecting to internal databases or remote engines and do not constitute unauthorized data exfiltration.
  • [PROMPT_INJECTION]: The skill defines a system for processing and storing arbitrary JSON data. While this represents a surface for indirect prompt injection if downstream consumers handle the data unsafely, the skill itself does not contain any malicious instructions or safety bypass attempts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 05:35 AM
Security Audit — agent-trust-hub — iii-state