skills/hsiangjenli/skills/spring-boot/Gen Agent Trust Hub

spring-boot

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches a project boilerplate from https://start.spring.io/starter.zip, which is the official and well-known Spring Initializr service.
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands, specifically curl for project generation and podman compose for local infrastructure management, as detailed in references/common.md.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface where user-supplied input is used to construct shell commands.
  • Ingestion points: User input for project name, package name, and Java version is requested in references/common.md.
  • Boundary markers: No explicit delimiters or boundary markers are defined in the curl command template to prevent argument injection.
  • Capability inventory: The skill uses curl (network access) and podman compose (container management) as documented in references/common.md.
  • Sanitization: The instructions lack specific guidance for the agent to sanitize or escape user-provided strings before they are inserted into the command templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 06:04 AM
Security Audit — agent-trust-hub — spring-boot