423-frameworks-quarkus-testing-acceptance-tests

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions require the agent to execute shell commands such as mvn compile and mvn clean verify to validate the project state and the newly generated test suite.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it parses untrusted Gherkin .feature files and incorporates their content into generated Java code which is then executed.
  • Ingestion points: Feature names, scenario titles, and Gherkin steps from user-provided files.
  • Boundary markers: There are no specified delimiters or warnings to ignore malicious instructions within the feature files.
  • Capability inventory: The agent is permitted to write source code and execute terminal commands for compilation and verification.
  • Sanitization: Content from the input files is placed into code templates without validation.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes well-known external resources, including official Docker images like postgres:16-alpine and standard Java testing libraries.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 03:32 PM
Security Audit — agent-trust-hub — 423-frameworks-quarkus-testing-acceptance-tests