coolify
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates application deployment from external sources like Git repositories and GitHub Actions, creating a surface for indirect prompt injection.
- Ingestion points: Git repository contents, branch names, and commit metadata are processed by Coolify during deployment (SKILL.md, references/deployment-strategies.md).
- Boundary markers: No specific delimiters or safety instructions are provided to the agent for handling potentially malicious instructions embedded in deployment data.
- Capability inventory: The skill uses
curlto interact with the Coolify API, which can trigger deployments and update configurations, including pre/post deployment commands and custom Docker options (references/api-patterns.md). - Sanitization: The documentation does not specify sanitization or validation routines for external content before it influences deployment actions.
Audit Metadata