ui-test-cypress
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a shell script
scripts/run-tests.shthat facilitates local test execution using the standardnpx cypress runcommand. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided project context to generate test plans and commands. The analysis identifies this as a potential attack surface where untrusted data could influence generated output, though the risk is low and consistent with the skill's purpose.
- Ingestion points: Project context, environment details, and constraints provided in the user prompt.
- Boundary markers: The instructions use structured headers but do not employ specific delimiters to isolate user-provided data from system instructions.
- Capability inventory: The skill has the capability to generate shell commands and includes a script for executing Cypress tests via
npx(scripts/run-tests.sh). - Sanitization: No explicit sanitization or validation of input context is performed before processing.
Audit Metadata