moai-cc-agents
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, obfuscation, or sensitive data access was detected. The skill consists of markdown documentation and agent templates.
- [COMMAND_EXECUTION]: The skill metadata defines access to tools like Bash and Task. While no actual commands are executed in the provided files, the architecture is designed to facilitate shell-based operations. The provided template follows security best practices by suggesting restricted tool access, such as limiting Bash to git commands.
- [PROMPT_INJECTION]: The skill describes a multi-agent system and inter-agent communication protocols. This design creates an inherent surface for indirect prompt injection via messages or task outputs from other agents, but the static templates do not contain any instructions to bypass safety guidelines or ignore previous rules.
Audit Metadata