bmad-qa-generate-e2e-tests

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a Python script located at {project-root}/_bmad/scripts/resolve_customization.py during its activation sequence.
  • [COMMAND_EXECUTION]: The workflow is designed to execute arbitrary instructions or shell commands defined in the activation_steps_prepend and activation_steps_append configuration fields.
  • [COMMAND_EXECUTION]: The agent is instructed to run the project's native test commands (e.g., npm test, playwright test) to verify the functionality of generated test files.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by loading and processing untrusted content from the project's codebase and configuration files while possessing command execution capabilities.
  • Ingestion points: Configuration files (customize.toml, config.yaml), context files matching **/project-context.md, and the project's source code files.
  • Boundary markers: Absent; the skill does not wrap ingested content in delimiters or provide instructions to ignore commands embedded in project data.
  • Capability inventory: Shell command execution via python3, execution of project-defined test suites, and file writing to the {default_output_file}.
  • Sanitization: Absent; no escaping, filtering, or validation is performed on the content read from external project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 03:39 AM
Security Audit — agent-trust-hub — bmad-qa-generate-e2e-tests