ddd-code-reviewer
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze source code, which constitutes a surface for indirect prompt injection. Malicious instructions could be embedded within code comments or metadata intended to override the agent's review logic. \n
- Ingestion points: Project source code files and fragments processed during the 'Code Scanning' phase in SKILL.md. \n
- Boundary markers: The instructions do not specify the use of clear delimiters or 'ignore' instructions when processing untrusted code snippets. \n
- Capability inventory: Across all scripts (SKILL.md, references/06-gotchas.md), the skill identifies issues and generates reports; it does not request capabilities for file system modification or external network access. \n
- Sanitization: No explicit sanitization or filtering of the ingested code is described in the references. \n- [EXTERNAL_DOWNLOADS]: The skill references the ArchUnit library in references/01-archunit-config.md and provides Maven/Gradle dependency coordinates (com.tngtech.archunit:archunit-junit5). These references point to well-known, trusted developer tools and registries, aligning with the skill's purpose of improving code quality.
Audit Metadata