История аудитов
building-multiagent-systems - 4 аудиты
Версия аудита 4
Последняя Средний рискJun 27, 2026, 04:17 PM
Static analysis reported many high-risk patterns, but review found Markdown architecture guidance and TypeScript-style examples rather than executable scripts or malicious code. The findings are mainly false positives from inline code, schema examples, and illustrative agent snippets. Publish with a warning because the skill discusses shell-capable agents, file access, and self-modifying workflows that require strict permissions in real implementations.
Capability review items (3)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Факторы риска
⚙️ Внешние команды (66)
Обнаруженные паттерны
Версия аудита 3
БезопасноJan 16, 2026, 01:01 PM
Pure documentation skill containing only markdown files with TypeScript pseudocode examples. No executable code, network calls, file system access, or external commands. All 118 static findings are false positives from the scanner misinterpreting documentation context. TypeScript template literals were flagged as shell backticks, and architectural terms triggered cryptographic/reconnaissance heuristics. The skill provides only educational architectural guidance.
Факторы риска
⚙️ Внешние команды (66)
Версия аудита 2
БезопасноJan 16, 2026, 01:01 PM
Pure documentation skill containing only markdown files with TypeScript pseudocode examples. No executable code, network calls, file system access, or external commands. All 118 static findings are false positives from the scanner misinterpreting documentation context. TypeScript template literals were flagged as shell backticks, and architectural terms triggered cryptographic/reconnaissance heuristics. The skill provides only educational architectural guidance.
Факторы риска
⚙️ Внешние команды (66)
Версия аудита 1
БезопасноJan 10, 2026, 09:10 AM
Pure prompt-based skill containing only markdown documentation and TypeScript pseudocode examples. No executable code, network calls, file access, or external commands. The skill provides architectural guidance through educational patterns and best practices.