coolify-compose

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is designed to ingest and analyze user-provided Docker Compose files as described in 'examples/README.md'. This ingestion of untrusted data creates a surface for indirect prompt injection.
  • Ingestion points: User-provided Compose files referenced in conversion examples.
  • Boundary markers: No explicit markers or 'ignore' instructions are used to delimit user data in the provided templates.
  • Capability inventory: The skill is restricted to generating YAML configurations; it does not contain code for host-level command execution, file system modification, or network requests.
  • Sanitization: No input validation or sanitization logic is present for the handled Compose files.
  • [CREDENTIALS_UNSAFE] (SAFE): Example 'before' files (e.g., 'examples/with-database/before.yml') contain hardcoded strings like 'supersecretpassword'. These are documented as illustrative placeholders for insecure configurations and do not represent active secrets or credential leaks.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 11:27 PM