cali-ops-docker-server-dashboard

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill reads ~/.ssh/config to identify server candidates for monitoring. This is a standard operation for SSH-based tools.
  • [COMMAND_EXECUTION]: Executes a local script (references/dashboard.sh) which uses ssh to connect to remote servers. It uses StrictHostKeyChecking=no and UserKnownHostsFile=/dev/null, which are common in automated dashboard tools to avoid interactive connection prompts.
  • [COMMAND_EXECUTION]: The remote script executes standard Docker and system commands (e.g., docker ps, df, free, crontab -l, tailscale status) to collect monitoring data.
  • [PROMPT_INJECTION]: The skill instructions contain directive language like 'MANDATORY' and 'CRITICAL', but these are used to define the intended operational flow for the agent rather than to bypass safety guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 10:48 AM
Security Audit — agent-trust-hub — cali-ops-docker-server-dashboard