skills/hussainweb/skills/coolify/Gen Agent Trust Hub

coolify

Pass

Audited by Gen Agent Trust Hub on Oct 31, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONPRIVILEGE_ESCALATIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill documentation includes instructions for patching older versions of Coolify by executing a remote shell script via curl -fsSL https://cdn.coollabs.io/coolify/patch.sh | sudo bash. Although this involves piped remote execution, the source is the official vendor domain for the platform managed by the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of docker-compose.yml, Dockerfile, and CI workflow files from user-controlled repositories.
  • Ingestion points: Git repository files including docker-compose.yml, Dockerfile, .env.example, and GitHub Actions workflow YAML files.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded prompts are utilized when reading these files.
  • Capability inventory: The skill is granted access to Bash, Read, Glob, Grep, and WebFetch tools, allowing for system-level interaction and network access based on the analyzed content.
  • Sanitization: There are no explicit sanitization steps for the contents of the analyzed files before they are processed by the agent.
  • [COMMAND_EXECUTION]: The skill provides numerous pre-defined commands to be executed via Bash, including Docker introspection (docker inspect), database queries (psql against the coolify-db container), and network checks (curl, nc, getent). These are strictly aligned with the skill's diagnostic and operational purpose.
  • [PRIVILEGE_ESCALATION]: Several operational steps require sudo privileges to manage system-level Docker configurations, registry credentials, and platform updates. These commands are typical for server administration tasks described in the skill.
  • [EXTERNAL_DOWNLOADS]: The skill references external resources from well-known services, including GitHub and Railway (npx skills add railwayapp/railpack), for extending its capabilities or obtaining configuration guidance.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 31, 2026, 04:35 PM