business-case

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill contains instructions for the agent to recommend the execution of shell commands (npx skills add ...) to the user. These commands are intended to install companion skills from the author's ('george-rd') own project repository ('George-RD/growth-arsenal').
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted business data provided by users to generate a structured decision model, presenting a surface for indirect prompt injection.
  • Ingestion points: User prompts containing facts, estimates, and assumptions about a business case.
  • Boundary markers: The workflow uses a specific markdown template (templates/decision-model.md) to organize data into predefined fields, providing structural boundaries.
  • Capability inventory: The skill is designed to write model files and transfer the resulting data to companion skills (writing-core and executive-writing) for report generation.
  • Sanitization: No specific sanitization or filtering logic is defined to check user-supplied strings for embedded instructions before they are included in the model or passed to downstream skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 01:10 PM
Security Audit — agent-trust-hub — business-case