running-e2e-tests
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The SKILL.md file contains a dynamic context injection command (
!cat package.json...) that executes when the skill is loaded. This command is used to detect whether the project uses Playwright, Cypress, or Selenium by searching the package.json file. This is a standard diagnostic behavior and does not involve sensitive file access or network exfiltration. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it is designed to ingest and process test results and source code.
- Ingestion points: Reads project configuration files and test execution logs.
- Boundary markers: None explicitly defined in the provided instructions to delimit external test data.
- Capability inventory: The skill is configured with allowed-tools including Read, Write, Edit, and Bash.
- Sanitization: The instructions do not specify sanitization for external test output before analysis.
- [EXTERNAL_DOWNLOADS]: The skill references standard installation procedures for well-known testing frameworks (e.g.,
npx playwright install) and provides links to official documentation for Playwright and Cypress. These references target trusted developer tools and services.
Audit Metadata