skills/mx-space/core/create-e2e-test/Gen Agent Trust Hub

create-e2e-test

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides a structured template for Vitest-based end-to-end tests. The template code focuses on standard database mocking, API interaction, and assertion patterns common in Node.js development.\n- [COMMAND_EXECUTION]: The documentation references standard shell commands (pnpm test) for executing the generated test suites. These are consistent with the skill's purpose as a developer tool.\n- [PROMPT_INJECTION]: The skill incorporates a surface for indirect prompt injection by using the $ARGUMENTS placeholder to define a file creation path without specifying validation requirements.\n
  • Ingestion points: The <module-name> provided via $ARGUMENTS in SKILL.md.\n
  • Boundary markers: Absent; the argument is directly interpolated into the file path string.\n
  • Capability inventory: The skill instructs the agent to create a new file based on the provided path and template.\n
  • Sanitization: There are no instructions or patterns provided to sanitize the input against path traversal sequences (e.g., ../).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 08:50 AM