create-test-project

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses opentaint and gradle commands to scaffold and build test projects within the .opentaint/ directory.
  • [DYNAMIC_EXECUTION]: The skill generates Java source code and YAML configurations at runtime, which are then compiled into models. This behavior is the core functional purpose of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external project data which presents a potential injection surface. 1. Ingestion points: Metadata from pom.xml and YAML tracking files in .opentaint/tracking/. 2. Boundary markers: None explicitly defined. 3. Capability inventory: Shell command execution (opentaint, gradle) and local file writing. 4. Sanitization: No specific sanitization of input metadata is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 02:13 AM
Security Audit — agent-trust-hub — create-test-project