400-frameworks-quarkus-create-project

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the SDKMAN (sdk) CLI to manage and install Java and Quarkus candidates on the system.
  • [COMMAND_EXECUTION]: The skill executes the Quarkus CLI (quarkus create app) to scaffold a new project and subsequently runs the Maven Wrapper (./mvnw) or Maven (mvn) to verify the project's integrity.
  • [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface by interpolating user-provided inputs (e.g., group ID, artifact ID, extensions) into shell commands.
  • Ingestion points: User-supplied project coordinates and extension lists gathered in Step 1 of the workflow.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the prompt templates.
  • Capability inventory: The agent is authorized to execute shell commands (sdk, quarkus, mvnw) and perform filesystem writes.
  • Sanitization: The instructions do not define explicit sanitization or validation logic for the user-provided arguments before shell execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:07 PM
Security Audit — agent-trust-hub — 400-frameworks-quarkus-create-project