manage-dns-records

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a set of domain-specific tools (e.g., DNS_getDNSRecordsV1, DNS_updateDNSRecordsV1) and the dig utility to perform DNS management tasks. These operations are consistent with the skill's stated purpose and include safety measures such as dry-run validation (DNS_validateDNSRecordsV1) and diff visualizations before execution.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process external DNS record data which presents a theoretical surface for indirect prompt injection.
  • Ingestion points: Results from DNS_getDNSRecordsV1 and DNS_getDNSSnapshotV1 containing user-controlled record content.
  • Boundary markers: None explicitly defined in the instructions for the received data.
  • Capability inventory: The agent has tools to modify DNS records, delete records, and restore snapshots.
  • Sanitization: The risk is mitigated by a mandatory human-in-the-loop confirmation step and the use of a formal validation tool prior to any mutation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 06:35 AM
Security Audit — agent-trust-hub — manage-dns-records