qe-requirements-validation
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the 'aqe' CLI tool for operations such as parsing Jira requirements, tracing tests, and generating Gherkin scenarios. These commands are standard for the tool's stated purpose of QE automation.\n- [DATA_EXFILTRATION]: Reads from local directories (
src/,docs/,tests/) and external Jira projects to perform traceability analysis. No suspicious network requests to non-whitelisted or unknown third-party domains were found.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its ingestion of untrusted data from requirements documents and Jira stories.\n - Ingestion points: Jira API data and local repository files (requirements, code, and markdown docs).\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands were found in the workflow tasks.\n
- Capability inventory: Subprocess execution via the 'aqe' CLI and file-system write access for generating feature files.\n
- Sanitization: No input validation or sanitization of the requirement text is documented before processing.
Audit Metadata