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