spring-boot-in-action

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [CREDENTIALS_UNSAFE]: Examples of hardcoded passwords such as "secret123" and "S3cr3tP@ss" are present in examples/before.md and evals/evals.json. These are explicitly documented as anti-patterns or utilized as test cases to verify the agent's ability to detect and remediate credential exposure.
  • [COMMAND_EXECUTION]: The skill includes a local Python script scripts/review.py designed to perform static analysis on source code. It uses regular expressions to identify common Spring Boot anti-patterns without executing the target code.
  • [PROMPT_INJECTION]: The skill is designed to ingest and review user-provided source code, which introduces a surface for indirect prompt injection.
  • Ingestion points: User-provided Java files and Spring configuration files (properties/YAML) are ingested in Code Review mode as defined in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the analyzed code.
  • Capability inventory: The skill uses scripts/review.py for local file scanning and provides suggestions for code modifications.
  • Sanitization: There is no explicit sanitization or filtering of comments or strings within the ingested source code.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 03:16 PM
Security Audit — agent-trust-hub — spring-boot-in-action