email-security

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for executing shell commands using common tools such as dig, swaks, and bash-based network redirection (/dev/tcp). These commands are standard for performing DNS reconnaissance and testing mail server responses.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted data from external DNS records which could contain malicious instructions. However, this is expected behavior for a security auditing tool. Ingestion points: DNS record strings retrieved via dig in SKILL.md. Boundary markers: Absent. Capability inventory: Access to shell commands for DNS and SMTP testing in SKILL.md. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 04:46 PM
Security Audit — agent-trust-hub — email-security