skills/adobe/skills/testing-blocks/Gen Agent Trust Hub

testing-blocks

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install well-known development and testing dependencies, including vitest, jsdom, and playwright, from the official npm registry. These are standard tools for web application testing.
  • [COMMAND_EXECUTION]: The documentation provides commands for executing local development tasks such as npm test, npm run lint, and running a temporary Playwright automation script. These actions are confined to the local development environment and are typical for the described workflow.
  • [PROMPT_INJECTION]: The skill contains a potential surface for indirect prompt injection as it involves an agent navigating to and inspecting local web pages (localhost:3000). However, given the context of testing locally developed components, this is considered a standard functional requirement.
  • Ingestion points: Automated browser navigation and content inspection via Playwright as described in SKILL.md.
  • Boundary markers: Not present in the provided script templates.
  • Capability inventory: Shell command execution via node, npm, and aem CLI tools across SKILL.md and resource files.
  • Sanitization: Not applicable as the testing targets locally authored code and content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 07:35 AM
Security Audit — agent-trust-hub — testing-blocks