docker-coolify
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is instructed to read
stack.mdto automate infrastructure scaffolding and verification. This constitutes an indirect prompt injection surface where content from a project file could be used to manipulate agent behavior. - Ingestion points: Reads and processes the
stack.mdfile. - Boundary markers: The instructions lack delimiters or warnings to ignore potentially malicious content within the processed file.
- Capability inventory: The agent can generate Dockerfiles, Docker Compose configurations, and prepare VPS deployment artifacts.
- Sanitization: No input validation or sanitization process is described for the content of
stack.md. - [EXTERNAL_DOWNLOADS]: The skill references official documentation and guidelines from well-known services such as Docker and Coolify.
Audit Metadata