coolify
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data that could contain malicious instructions designed to influence agent behavior.\n
- Ingestion points: The skill reads external deployment logs (
coolify app deployments logs) and local environment variable files (.env.production).\n - Boundary markers: No specific delimiters or warnings are used to separate this external content from the agent's instructions.\n
- Capability inventory: The agent has the ability to trigger deployments, modify environment configurations, and manage database services.\n
- Sanitization: There is no evidence of sanitization or filtering of the ingested content before it is processed by the agent.\n- [COMMAND_EXECUTION]: The skill utilizes local shell commands to interact with the Coolify infrastructure.\n
- Evidence: Usage of the
coolifyCLI andcurlcommands for application management and API interactions.\n- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing necessary CLI tools from external sources.\n - Evidence: References installation via Homebrew and Go from the official coollabsio organization on GitHub.
Audit Metadata