design-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill mentions
bun run verifyandbun run verify:allinSKILL.mdas verification steps. These are standard task runner commands for local environment testing and do not demonstrate malicious intent. - [EXTERNAL_DOWNLOADS]: The
references/catalog.jsonfile contains multiple URLs pointing torefactoring.guru, a well-known educational resource for design patterns. These links are for informational purposes and do not trigger remote code execution or automated downloads of executable scripts. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided code to diagnose design problems. This is a common pattern for AI agent skills. While it represents an ingestion point for potentially untrusted data, the skill includes structured references (
selection-guide.md,catalog.json) and a formal decision record (decision-record.md) that provide context boundaries for the agent's analysis.
Audit Metadata