qe-risk-based-testing
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process external data sources such as bug databases, source code changes, and production incident reports to calculate risk scores. This creates a surface for indirect prompt injection where malicious instructions embedded in these external datasets could influence the agent's prioritization or test generation logic.
- Ingestion points: Data enters the agent's context through parameters like
bugDatabase,changedFiles, andproduction-datawithin theTaskand CI/CD examples. - Boundary markers: The provided examples do not include explicit delimiters or system instructions to ignore potential commands embedded within the processed data.
- Capability inventory: The skill interacts with other agents for test generation (
qe-test-generator) and risk analysis (qe-regression-risk-analyzer), and includes examples of triggering shell commands (npm run test) based on processed results. - Sanitization: No evidence of data sanitization, validation, or escaping is present in the skill's logic for handling external inputs.
Audit Metadata