Skills
skills/pluginagentmarketplace/custom-plugin-software-design/domain-driven-design/Gen Agent Trust Hub

domain-driven-design

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill accepts untrusted data through the domain_description parameter (max 10,000 characters).
  • Ingestion points: domain_description field in the SkillParams interface (SKILL.md).
  • Boundary markers: None. The instructions do not define delimiters for the input text.
  • Capability inventory: The skill produces domain models and emits events (domain_modeled) consumed by other agents like 05-domain-driven and 07-architecture-patterns.
  • Sanitization: No input sanitization or filtering logic is present in the scripts.
  • Unsafe Deserialization (SAFE): The validation script scripts/validate.py correctly uses yaml.safe_load(), mitigating potential code execution via YAML tags.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 05:02 AM