multi-agent-vcs
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [PROMPT_INJECTION] (SAFE): No malicious instructions, bypass markers, or role-play jailbreaks were detected. The included subagent prompt template is a legitimate operational constraint for workflow coordination.
- [COMMAND_EXECUTION] (LOW): The skill provides documentation for standard command-line tools including 'git', 'gt' (Graphite), and 'but' (GitButler). These are listed as functional examples for version control management and do not execute arbitrary or malicious code.
- [DATA_EXFILTRATION] (SAFE): There are no patterns indicating access to sensitive credential files or unauthorized network communication.
- [EXTERNAL_DOWNLOADS] (SAFE): The skill does not perform any runtime package installations or remote script executions.
Audit Metadata