acceptance-testing
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (MEDIUM): The skill is designed to convert external inputs (requirements, user stories) into executable test scenarios and plans.
- Ingestion points: Processes user-provided requirements or user stories as defined in the 'Inputs' and 'Workflow' sections.
- Boundary markers: Absent. There are no instructions to the agent to treat requirement text as data only or to ignore embedded instructions within those requirements.
- Capability inventory: The skill description explicitly mentions it can 'implement or execute user acceptance tests (UAT)', which implies the ability to run code, interact with browsers (Playwright/Cypress), or use CLI tools.
- Sanitization: None. The skill does not provide methods for escaping or validating the content of the requirements before they are used to generate test logic.
- Unverifiable Dependencies (LOW): The skill recommends several third-party tools (Playwright, Cypress, insta). While these are industry-standard, the skill relies on the existing environment's versions and does not verify the integrity of these tools if the agent were to install them.
Audit Metadata