Skills
Navigate
skills/pramoddutta/qaskills/Behave BDD Testing/Gen Agent Trust Hub

Behave BDD Testing

Pass

Audited by Gen Agent Trust Hub on Sep 27, 2026

Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill includes hardcoded example credentials such as "SecurePass123" and "AdminPass123" within Gherkin scenarios for testing login functionality.
  • [COMMAND_EXECUTION]: The CI/CD configuration example provides shell commands for installing dependencies and the Google Chrome browser.
  • [PRIVILEGE_ESCALATION]: The GitHub Actions example uses sudo to install system packages, which is a common but privileged operation in CI environments.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines step definitions that ingest data from external Gherkin tables, creating a surface for potential indirect prompt injection.
  • Ingestion points: Data enters the context via context.table in auth_steps.py and api_steps.py.
  • Boundary markers: There are no explicit boundary markers or instructions to ignore potential commands embedded within the table data.
  • Capability inventory: The skill utilizes requests for network operations and selenium for browser automation.
  • Sanitization: The implementation lacks sanitization or validation of the ingested strings before they are used in automation tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 27, 2026, 10:41 AM