bmad-build-auto
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external project documentation such as tickets and requirements to drive its planning and coding stages.\n
- Ingestion points:
step-01-clarify-and-route.mdreads ticket files, epics, and initiative documents.\n - Boundary markers: Employs
<intent-contract>tags inplan-template.mdto isolate read-only instructions.\n - Capability inventory: Has file-write permissions, executes shell commands via
uvandgit, and manages subagents.\n - Sanitization: Instructions in
edge-case-hunter.mdandverification-gap.mdrestrict subagent behavior to textual analysis and prohibit external tool use.\n- [COMMAND_EXECUTION]: The skill triggers the execution of local project scripts and repository management tools.\n - Evidence:
SKILL.mddirects the user to runuv runforrender_skill.py;step-01andstep-03executetickets.pyandgit.\n- [EXTERNAL_DOWNLOADS]: The skill references its remote source code in a GitHub repository managed by the author.\n - Evidence:
bmod.tomlidentifies the source asgithub:bmad-code-org/BMAD-METHOD/skills/method.
Audit Metadata