email-diagnostics
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill serves as a static documentation and routing resource. It guides the agent or user through diagnostic paths for email deliverability issues without performing any automated or hidden actions.
- [COMMAND_EXECUTION]: Provides standard, benign command-line examples using the
digutility to verify DNS records (SPF, DKIM, and DMARC). These examples are purely instructional and represent industry-standard troubleshooting practices. - [INDIRECT_PROMPT_INJECTION]: The skill identifies inbound email processing as a potential risk for AI agents and proactively advises on the implementation of security measures, including sanitization, Unicode stripping, and prompt injection detection. As this is a documentation skill that does not process external data itself, this represents a defensive guidance pattern.
Audit Metadata