cold-email-deliverability

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute system commands, specifically 'dig', to perform DNS lookups for verifying mail server configurations.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of DNS TXT records (SPF, DKIM, DMARC). There is a theoretical risk that an attacker-controlled domain could host records containing natural language instructions designed to subvert the agent's logic during the parsing and scoring phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 10:28 PM
Security Audit — agent-trust-hub — cold-email-deliverability