qa-game

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads external, user-provided data from files like design-brief.md and game source code to determine test logic and audit entity interactions. This data could contain malicious instructions that influence the agent's behavior during the test generation or auditing phase.
  • Ingestion points: design-brief.md, package.json, vite.config.js, src/main.js, src/core/GameState.js, src/core/EventBus.js, src/core/Constants.js, and various scene files.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill when reading these files.
  • Capability inventory: The skill has the capability to read and write to the local file system (including modifying src/main.js and package.json) and execute shell commands (npm test).
  • Sanitization: The skill does not specify any sanitization, validation, or filtering for the content ingested from the project files.
  • [COMMAND_EXECUTION]: The skill performs shell operations to set up the testing environment and execute the generated test suite.
  • Evidence: Utilizes mkdir -p, cp (copying files from the plugin root), and npm test / npm run commands.
  • [DYNAMIC_EXECUTION]: The skill generates JavaScript and configuration files (.js, .mjs) based on game logic templates and then executes them via a test runner.
  • Evidence: Creates test files in the tests/ directory and helpers in scripts/, which are subsequently executed during the verification step.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 11:54 PM