email-deliverability

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides educational content and troubleshooting advice for email authentication (SPF, DKIM, DMARC) and reputation management. No dangerous commands or sensitive data access patterns were identified.
  • [COMMAND_EXECUTION]: The provided scripts/verify.sh utility is a read-only linter that uses grep and awk to scan local files (such as DNS zone files or configurations) for insecure mail authentication settings like +all in SPF or missing report addresses in DMARC. It does not perform network operations or resolve DNS.
  • [EXTERNAL_DOWNLOADS]: The skill mentions external providers and services (e.g., Gmail, Yahoo, DigiCert, GlobalSign) but does not include any automated download or remote script execution triggers. References to these services are for configuration context and documentation.
  • [PROMPT_INJECTION]: The evals/cases.yaml file contains prompt examples for testing the agent's routing logic. These are standard evaluation test cases and do not contain instructions to bypass safety filters or override core agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 09:36 PM
Security Audit — agent-trust-hub — email-deliverability