multi-platform-apps-multi-platform

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data from the initial feature specification and interpolates it directly into instructions for various sub-agents.
  • Ingestion points: The $ARGUMENTS variable is used in the Phase 1, Step 1 prompt to define the feature design.
  • Boundary markers: There are no delimiters (e.g., XML tags or triple quotes) or explicit "ignore embedded instructions" warnings surrounding the user-provided content in the prompts.
  • Capability inventory: The workflow orchestrates agents (backend-architect, ui-ux-designer, frontend-developer, etc.) that are expected to generate code, design specifications, and documentation across multiple files.
  • Sanitization: The instructions do not include any steps to validate or filter the content of $ARGUMENTS before it is processed by the AI agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:04 PM
Security Audit — agent-trust-hub — multi-platform-apps-multi-platform