hcloud-dns

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to execute various hcloud CLI commands to manage DNS infrastructure, including zone lifecycle and record management.- [INDIRECT_PROMPT_INJECTION]: The skill includes operations that read data from external DNS zones, which could be exploited if the data contains malicious instructions.
  • Ingestion points: Data is loaded into the context through commands like hcloud zone list, hcloud zone rrset list, and the import-zonefile functionality (SKILL.md).
  • Capability inventory: The skill enables the agent to create, update, and delete DNS zones and RRSets, providing high control over the environment.
  • Boundary markers: None identified in the instruction set to separate record content from instructions.
  • Sanitization: There is no mention of filtering or sanitizing input retrieved from the Hetzner API or zone files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 07:30 PM
Security Audit — agent-trust-hub — hcloud-dns