software-design-review
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is strictly instructional and provides a framework for architectural code reviews. It uses static text and code examples to define principles like module depth and information hiding.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code ($ARGUMENTS), which is a common vector for indirect prompt injection. However, the detailed scoring criteria and 'Red Flag' system provide a structured environment that helps mitigate the risk of the agent following instructions embedded within the analyzed code. The severity is low as this is inherent to the skill's purpose.\n- [SAFE]: All code snippets provided in the documentation are for illustrative purposes (showing 'Good' vs 'Bad' patterns) and do not perform any sensitive operations or access credentials. The referenced technologies (Tauri, Rust, React) are part of the stated project context and no malicious libraries are requested.
Audit Metadata