game-perf-profiling

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses official documentation and tools from well-known services (Unity and Epic Games) for performance analysis and automated testing. All external references target trusted documentation domains.
  • [COMMAND_EXECUTION]: The skill provides standard bash commands for executing Unity tests in batch mode within a CI environment. This is a common and expected practice for automated performance regression testing.
  • Evidence: SKILL.md Step 7 provides the command: unity -batchmode -runTests -testPlatform StandaloneWindows64 -testResults results.xml -projectPath ..
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data files, such as Unity profile captures and CI test results, which is a standard requirement for its performance profiling functionality.
  • Ingestion points: Processes binary profile data files (.data, .pdata) and XML test result files (results.xml) in SKILL.md (Steps 2 and 7).
  • Boundary markers: The instructions do not define specific delimiters for separating processed data from agent instructions.
  • Capability inventory: Includes instructions for shell command execution to run automated tests.
  • Sanitization: No specific sanitization or validation steps are mentioned for the ingested performance data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 10:00 AM