ab-test-setup
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied JSON files (test results and configurations) and interpolates this data into reports. If these files contain malicious instructions, they could influence the agent's behavior during analysis.
- Ingestion points:
results_analyzer.py(reads test results) andtest_designer.py(reads test configurations). - Boundary markers: None present. The scripts do not use delimiters or provide instructions to the agent to ignore embedded commands in the data.
- Capability inventory: The skill is limited to mathematical processing and console output. It contains no network operations, subprocess executions, or file-writing capabilities across
results_analyzer.py,sample_size_calculator.py, andtest_designer.py. - Sanitization: Content from JSON fields (like test names or hypotheses) is reflected directly in the output without escaping or validation.
Audit Metadata