bmad-qa-generate-e2e-tests

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local scripts located in the project's _bmad/scripts/ directory using uv run to handle configuration and customization logic.
  • [COMMAND_EXECUTION]: The workflow identifies and executes the project's native test runner (e.g., Playwright, Jest) to verify the functionality of generated test files.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the project's codebase, including source files, dependency manifests, and content from files matched by user-defined globs.
  • Ingestion points: Reads project source code from directories like src/components/ and files specified in the persistent_facts list.
  • Boundary markers: None explicitly defined for separating ingested file content from agent instructions.
  • Capability inventory: Executes shell commands through uv run and various test frameworks; performs file system writes to save test summaries.
  • Sanitization: No specific sanitization or validation of ingested project data is described.
  • [EXTERNAL_DOWNLOADS]: The skill contains references to external resources, specifically pointing to documentation hosted on the vendor's official domain (bmad-code-org.github.io).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 10:42 PM
Security Audit — agent-trust-hub — bmad-qa-generate-e2e-tests