coolify-troubleshoot

Fail

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructs the agent to execute a remote script directly in the shell: 'curl -fsSL https://cdn.coollabs.io/coolify/install.sh | bash'. This pattern bypasses inspection of the script before execution.
  • [COMMAND_EXECUTION]: The skill gives the agent access to numerous high-privilege system commands, including 'docker exec', 'docker restart', and 'systemctl'. This provides significant control over the server environment.
  • [EXTERNAL_DOWNLOADS]: Downloads configuration and installation scripts from 'coollabs.io'.
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by directing the agent to read and act upon output from 'docker logs' and 'dmesg', which may contain attacker-controlled content from external applications.
  • Ingestion points: SKILL.md (via 'docker logs', 'dmesg', 'docker events').
  • Boundary markers: None provided to isolate untrusted data.
  • Capability inventory: Subprocess execution ('docker exec', 'docker restart'), network operations ('curl').
  • Sanitization: None provided.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cdn.coollabs.io/coolify/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jun 16, 2026, 01:04 AM
Security Audit — agent-trust-hub — coolify-troubleshoot