atlas
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust architectural analysis framework based on established industry standards (ISO/IEC/IEEE 42010:2022) and recognized methodologies (C4 models, DDD Bounded Contexts).
- [SAFE]: External dependencies and tools referenced (e.g., madge, dependency-cruiser, ArchUnit, SonarQube) are industry-standard utilities for static analysis and architectural enforcement.
- [SAFE]: The skill establishes clear boundaries and handoff patterns, ensuring it does not modify code directly but instead provides actionable proposals via ADRs and RFCs.
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze project source code (untrusted data) during its SURVEY phase. While this is necessary for its primary purpose, it presents a theoretical surface for indirect prompt injection if the source code contains adversarial comments or structures. This risk is inherent to the skill's utility and no specific malicious triggers were found.
Audit Metadata