401-frameworks-quarkus-core

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the execution of shell commands such as ./mvnw compile and ./mvnw clean verify. These are standard procedures for validating Java and Quarkus applications during development and refactoring, allowing the agent to ensure code correctness via the local build system.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted user project files (source code and Maven configuration) and has the capability to execute commands. A malicious project could theoretically attempt to exploit the build process.
  • Ingestion points: The skill reads the local Java project structure, source files, and Maven configuration.
  • Boundary markers: No explicit delimiters are specified to isolate project content from the agent's internal instructions.
  • Capability inventory: The agent is authorized to execute shell commands through the Maven build system (mvnw).
  • Sanitization: No sanitization is performed on project files before the build commands are executed, relying on the user's local environment security.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 11:00 AM
Security Audit — agent-trust-hub — 401-frameworks-quarkus-core