bmad-idea

Warn

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation provides installation instructions using a command that fetches content from an unverified third-party GitHub repository (github.com/supercent-io/skills-template).\n- [COMMAND_EXECUTION]: The skill requests permission to use the Bash tool, which allows the agent to execute arbitrary shell commands on the system.\n- [EXTERNAL_DOWNLOADS]: Reference material points to an upstream module repository (github.com/bmad-code-org/bmad-module-creative-intelligence-suite) which is not a verified vendor source.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes creative inputs within complex agent workflows without isolation.\n
  • Ingestion points: User-provided text for brainstorming, design thinking, and storytelling workflows in SKILL.md.\n
  • Boundary markers: Absent; no specific delimiters are defined to separate user-provided data from agent instructions.\n
  • Capability inventory: The skill utilizes Bash, Write, Read, Grep, and Glob tools.\n
  • Sanitization: No input validation or sanitization procedures are documented for external creative data.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 20, 2026, 07:00 AM