qa-test-generate
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill ingests and processes untrusted data from BDD test cases and code scaffolds, which serves as an indirect prompt injection surface where malicious instructions could influence the test generation process.
- Ingestion points: Step 1 (Reading qa-test-cases, backend-scaffold, frontend-scaffold, and api-contract files)
- Boundary markers: Absent (no explicit delimiters or instructions to ignore embedded commands in the input data)
- Capability inventory: Write ($JAAN_OUTPUTS_DIR), Task (shell sourcing), and Edit (configuration modification)
- Sanitization: Absent (no validation or filtering of input content before processing)
- [COMMAND_EXECUTION]: The skill utilizes the 'Task' tool and sources internal shell scripts ('id-generator.sh' and 'index-updater.sh') from the plugin root to manage IDs and project indices.
- [EXTERNAL_DOWNLOADS]: The skill uses 'WebSearch' for research purposes and provides instructions for users to perform external package installations via npm/npx for test runners and mock libraries.
Audit Metadata