spf-dkim-dmarc-setup
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes shell command snippets for verifying DNS records and processing local files.
- Evidence: Use of
dig,grep,wc, andgunzipin SKILL.md for DNS status checks and report parsing. - Context: These are standard diagnostic utilities for email administration and are used here for their intended purpose without evidence of privilege escalation or malicious intent.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for analyzing external DMARC reports (aggregate XML files).
- Ingestion points: The skill reads external data from
report.xml.gz(SKILL.md). - Boundary markers: No explicit boundary markers are present in the processing instructions.
- Capability inventory: The skill utilizes
dig,grep,wc, andgunzipvia shell execution. - Sanitization: The provided command uses
grep -oEwith a specific regular expression to extract only recognized XML tags (source_ip,disposition,dkim,spf). This strict extraction pattern prevents the agent from processing or obeying arbitrary text or malicious instructions that might be embedded in a DMARC report file.
Audit Metadata