check-communication
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill is limited to providing linguistic and tonal guidance for text messages.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied drafts (SKILL.md) which are not explicitly delimited. However, there are no dangerous capabilities (no network, file, or command tools) available to the agent in this context, and no sanitization is required for this text-only task.
Audit Metadata