dh-deploy

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from application catalogs and service lists, creating a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent context via the dokploy_list_templates and dokploy_list_apps tools.
  • Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or ignore embedded instructions when processing template metadata or app configurations.
  • Capability inventory: The skill utilizes high-impact tools including dokploy_deploy_template, dns_create_record, ssh_exec, and dokploy_redeploy.
  • Sanitization: There are no instructions for sanitizing or validating external data retrieved from the tools before it is used to parameterize deployment commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 07:16 PM
Security Audit — agent-trust-hub — dh-deploy