peach-agent-team
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill verifies the 'CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS' flag in the local
~/.claude/settings.jsonfile. This is a legitimate configuration check for the required environment. - [COMMAND_EXECUTION]: Orchestration workflows involve executing standard development tools such as
bun test,bun run build, andvue-tscto ensure code quality and functional integrity. - [EXTERNAL_DOWNLOADS]: The skill references documentation on the author's GitHub repository (
peachSolution) and uses a Figma MCP tool to fetch design data from user-provided URLs. These are recognized as safe vendor and well-known service resources. - [PROMPT_INJECTION]: The skill processes external design data and database schemas, representing a surface for indirect prompt injection. However, this is necessary for its primary function as a code generator, and no malicious patterns or safety bypass attempts were found.
Audit Metadata