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
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 06:19 AM