bmad-cis-innovation-strategy

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local script {project-root}/_bmad/scripts/resolve_customization.py during both the activation and completion steps. This script is used to merge configuration settings from the skill's root and project-specific customization files. This execution is part of the established orchestration for the bmad-code-org toolkit.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted data from the project directory and user-provided attributes.
  • Ingestion points: Persistent facts are loaded from {project-root}/**/project-context.md and the data attribute.
  • Boundary markers: No explicit delimiters (like XML tags or markdown blocks) are used to isolate ingested project context from the primary instructions.
  • Capability inventory: The skill has the ability to execute local Python scripts and perform file system writes for saving strategy artifacts.
  • Sanitization: There is no evidence of filtering or sanitization performed on the ingested file contents or user data prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 05:56 AM