spring-boot

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute standard build and run commands using the project's local wrapper scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-provided source code, creating a potential vector for indirect prompt injection.
  • Ingestion points: The instructions in SKILL.md prompt the agent to review, scaffold, and refactor Spring Boot applications provided by the user.
  • Boundary markers: The skill does not implement specific delimiters or instructions to treat user-provided code as untrusted data or to ignore embedded instructions.
  • Capability inventory: The agent is guided to execute shell commands such as ./mvnw test, ./mvnw spring-boot:run, and ./gradlew bootRun as part of the verification workflow in references/workflows.md.
  • Sanitization: The skill lacks sanitization logic or input validation to filter potentially malicious prompt injection patterns within the code it reviews.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 10:12 PM
Security Audit — agent-trust-hub — spring-boot