bmad-qa-generate-e2e-tests
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands using the
uvtool to run internal project scripts. Specifically, it executes{project-root}/_bmad/scripts/render_skill.pyand{project-root}/_bmad/method/scripts/tickets.py. These scripts are part of the BMad framework integrated into the user's project repository. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from project documentation and ticket management files to generate test scenarios, creating a surface for indirect instructions.
- Ingestion points: The skill reads epic files, story files, ticket descriptions (
verifyanddescriptionfields), and project source code into the agent's context inworkflow.md. - Boundary markers: No explicit boundary markers or instructions to disregard embedded commands are present when the skill interpolates this external content into its workflow.
- Capability inventory: The skill possesses the capability to read and write files (creating new test files) and execute shell commands through the
uv runinterface. - Sanitization: The instructions do not specify any sanitization or validation logic for the content retrieved from the ticket system or project files.
Audit Metadata