agent-orchestrator
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely instructional and does not contain any executable scripts, binary files, or suspicious shell commands.
- [SAFE]: No evidence of prompt injection or attempts to bypass safety filters was found; the content focuses on task decomposition and delegation logic.
- [SAFE]: Mentions of external platforms (GitHub, Supabase, Playwright) are documented as tool capabilities for specialized agents within a developer workflow context and do not involve credential harvesting or unauthorized access.
- [SAFE]: The skill includes explicit security mitigations for indirect injection scenarios, such as the 'Validate Handoffs' best practice which advises checking output formats and validating data against schemas before passing it between agents.
Audit Metadata