scaffold-quarkus-mcp-server

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell operations using curl, unzip, and mvn to fetch, extract, and build the generated project. These actions are aligned with the skill's purpose of project scaffolding.
  • [EXTERNAL_DOWNLOADS]: The skill downloads project archives from code.quarkus.io, the official developer portal for the Quarkus framework.
  • [INDIRECT_PROMPT_INJECTION]: User-provided project coordinates (such as artifactId) are used directly in shell commands, creating a surface for potential command injection if the inputs are not sanitized.
  • Ingestion points: User-specified groupId, artifactId, version, and target directory collected in Step 1.
  • Boundary markers: None identified in the shell command templates.
  • Capability inventory: Execution of curl, unzip, and mvn via SKILL.md (Steps 2, 7, and 8).
  • Sanitization: There are no instructions to sanitize or validate the user-provided strings before they are used in shell execution.
  • [DYNAMIC_EXECUTION]: The skill generates Java source and test files from reference templates and immediately executes them using mvn verify or mvn test to validate the scaffolded project.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 03:04 PM