bmad-idea

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to facilitate creative workflows such as brainstorming, design thinking, and storytelling. Analysis confirms that the behavior matches its stated purpose.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and an installation source on GitHub (github.com/akillness/oh-my-skills and github.com/bmad-code-org/bmad-module-creative-intelligence-suite). These resources are consistent with the vendor and project identity and represent legitimate external references.
  • [COMMAND_EXECUTION]: The skill is configured with access to Bash, Read, and Write tools. These are used to manage creative sessions and store outputs in a local directory (./creative-outputs/). No suspicious or unauthorized command patterns were found.
  • [PROMPT_INJECTION]: The skill ingests untrusted user input for creative tasks (brainstorming, problem-solving) and has access to powerful tools (Bash). This creates an indirect prompt injection surface.
  • Ingestion points: User-provided text for ideation sessions.
  • Boundary markers: The instructions do not define specific delimiters for separating user data from system instructions.
  • Capability inventory: Read, Write, Bash, Grep, Glob tools are accessible.
  • Sanitization: No explicit sanitization or validation of the user-provided data is mentioned.
  • Note: This is identified as a functional surface typical of creative assistants and does not involve malicious logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 09:05 AM