Audit Dockerfiles + image configs for security smells
Single tool 'dockeraudit_scan' has a basic description (67 chars) and minimal input schema. The tool name lacks a clear action verb (scan is acceptable but generic). Input parameter 'target' has a description but no type constraints, format guidance, or examples. No output schema is documented, the tool returns JSON but the structure is not formally specified. No error handling guidance, no parameter validation rules, and no security considerations documented. The implementation is simple but the definition quality falls well below production standards.
Audit Dockerfiles + image configs for security smells. Returns JSON findings.
No output schema documented. Tool returns JSON findings but structure is not formally specified for LLM consumption.
Input parameter 'target' lacks type constraints, format guidance, and validation rules. Should specify: file vs directory, path format, allowed extensions, max depth.
No error handling guidance. Tool description does not explain failure modes (file not found, permission denied, invalid path) or recovery steps.
Tool name 'dockeraudit_scan' is generic. Verb 'scan' does not clearly distinguish this from other audit/scan tools. Consider 'audit_dockerfile' or 'scan_dockerfile_security'.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 43 | 2026-07-28+ | v2 |
No pagination or result limiting documented. If scanning large directory trees, response could be unbounded and exhaust context window.