test-architect

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the 'uv' tool to execute internal Python scripts ('coverage-analyzer.py', 'edge-case-generator.py', and 'flaky-test-analyzer.py') for data processing. These scripts are local to the skill package and do not perform network operations. Additionally, the skill creates a temporary HTML file to display analysis results in a web browser.
  • [PROMPT_INJECTION]: The skill analyzes untrusted data from external sources, creating a surface for indirect prompt injection.
  • Ingestion points: The skill reads source code, coverage reports (JSON/LCOV), and test logs during analysis.
  • Boundary markers: The instructions lack explicit boundary markers or directives to ignore instructions contained within the analyzed data.
  • Capability inventory: The skill can execute commands via the agent to run analysis scripts and open the generated dashboard.
  • Sanitization: While the dashboard template uses HTML escaping for data injection, there is no logic to sanitize or filter natural language instructions found in the analyzed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 02:19 AM