community-push-broadcast
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill mandates a multi-step workflow including target resolution, drafting, and spellchecking before any notification action occurs.
- [SAFE]: Explicit user confirmation is strictly required before the final broadcast tool is invoked, effectively preventing accidental or automatic sends.
- [SAFE]: Input guardrails are implemented to reject empty or placeholder content and enforce character length limits to ensure quality.
- [SAFE]: No patterns of prompt injection, data exfiltration, obfuscation, or malicious code execution were detected in the skill instructions or workflow definition.
Audit Metadata