spring-boot-initializr

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The script scripts/generate-spring-boot-project.py fetches project archives from https://start.spring.io/starter.zip, which is the official endpoint for the Spring Initializr service. This is a well-known and trusted service in the Java ecosystem.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its handling of user-supplied project metadata.
  • Ingestion points: User-provided artifactId in scripts/generate-spring-boot-project.py is used as the base path for file operations.
  • Boundary markers: No boundary markers or specific instructions are provided to the agent to treat the artifactId as untrusted data or to validate its format.
  • Capability inventory: The script scripts/generate-spring-boot-project.py performs directory creation (os.makedirs) and ZIP extraction (zipfile.extractall) to the local file system.
  • Sanitization: The script does not perform any sanitization or path validation on the artifactId parameter, which could allow a malicious user to specify a path like ../../some/dir to write files outside of the intended project directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 01:17 PM
Security Audit — agent-trust-hub — spring-boot-initializr