moai-workflow-loop
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements automated code quality and security scanning workflows. It includes specific examples for fixing hardcoded secrets and preventing XSS, demonstrating a security-conscious design.
- [EXTERNAL_DOWNLOADS]: The instructions recommend installing various official language servers and the moai-adk tool from the author's GitHub repository (github.com/modu-ai/moai-adk). These resources are recognized as safe vendor-owned or well-known services.
- [PROMPT_INJECTION]: An indirect prompt injection surface is present as the skill ingests and processes data from external tools.
- Ingestion points: LSP diagnostics, AST-grep scan results, and test runner outputs are collected by the post_tool__lsp_diagnostic and stop__loop_controller hooks.
- Boundary markers: Explicit delimiters for tool outputs are not specified in the documentation.
- Capability inventory: The agent has access to Write, Edit, Bash, Grep, and Glob tools.
- Sanitization: No explicit sanitization or filtering of external tool output is documented.
Audit Metadata