402-frameworks-quarkus-rest

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires running shell commands such as ./mvnw compile and mvn clean verify to validate code changes.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection from files in the project being analyzed.
  • Ingestion points: The agent reads Java source code, Maven configuration (pom.xml), and OpenAPI contracts.
  • Boundary markers: None are specified to isolate the untrusted project data from the instructions.
  • Capability inventory: The agent executes shell commands via Maven, which can be misused if the project configuration is malicious.
  • Sanitization: No sanitization of project files or build environments is performed prior to command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 08:15 PM