create-spring-boot-java-project

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches a project skeleton from Spring Initializr (start.spring.io), which is a well-known service for bootstrapping Spring applications.
  • [INDIRECT_PROMPT_INJECTION]: The skill interpolates user-provided variables directly into shell commands used for downloading and extracting the project.
  • Ingestion points: The variable ${input:projectName} is used within curl, unzip, and cd commands in SKILL.md.
  • Boundary markers: No specific boundary markers or delimiters are used to isolate user input from the surrounding shell command context.
  • Capability inventory: The skill possesses the capability to perform network requests (curl), filesystem modifications (unzip, rm), and command execution (./mvnw).
  • Sanitization: The instructions do not include steps for the agent to sanitize or validate the user-provided project name to prevent shell metacharacter injection.
  • [COMMAND_EXECUTION]: The skill executes the Maven Wrapper (./mvnw) script to verify the project. While this script is downloaded from an external source, it is a standard component of projects generated by the Spring Initializr service.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 02:24 PM