swarm-meeting
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust orchestration pattern for design reviews using localized role emulation and clear operating rules. Analysis of the instructions and configuration files reveals no attempts at prompt injection or safety bypass.
- [SAFE]: The included Python scripts, 'render_meeting_context.py' and 'select_profile.py', perform legitimate configuration management tasks. They are restricted to reading the skill's own JSON-formatted profile and markdown prompt files. There are no network operations, subprocess executions, or accesses to sensitive system files or credentials.
- [SAFE]: All dependencies, role definitions, and workflow rules are provided as local artifacts within the skill package, minimizing supply chain risks and ensuring predictable behavior.
Audit Metadata