software-architecture-design
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is primarily composed of instructional markdown and configuration files that define architectural best practices. It does not include any scripts, binaries, or automated command execution logic.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to analyze repository evidence (code, state, and constraints) to make architectural decisions. This creates an attack surface for indirect prompt injection where an attacker could place malicious instructions inside the repository being analyzed. However, this is a fundamental part of the skill's functionality and the instructions focus on logical analysis rather than executing content from the repository.
- [EXTERNAL_DOWNLOADS]: The documentation contains references to official technical resources, including Amazon Web Services (AWS) architectural guides and the JSON Schema specification. These references target well-known, trusted technical services and do not involve the execution of remote code.
Audit Metadata