NYC

spring-boot-dependency-injection

Fail

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION] (HIGH): The skill is highly vulnerable to Indirect Prompt Injection due to the combination of reading external content and having high-privilege tool access.\n
  • Ingestion points: The agent is instructed to use Glob, Grep, and Read to analyze Java source files and build configurations (e.g., pom.xml, build.gradle) which are attacker-controllable.\n
  • Boundary markers: None. There are no instructions for the agent to ignore or delimit embedded natural language instructions found within the code being analyzed.\n
  • Capability inventory: The agent has Bash (for executing build tests), Write, and Edit capabilities, allowing an injection to result in code modification or arbitrary command execution.\n
  • Sanitization: No sanitization or validation of external code content is required before processing.\n- [COMMAND_EXECUTION] (MEDIUM): The workflow requires the agent to execute local build scripts (./gradlew test and mvn test). This presents a security risk where a malicious repository can exploit the agent's Bash tool to execute arbitrary code hidden within the build wrappers or test suite configuration.
Recommendations
  • AI detected serious security threats
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 09:01 PM