@1892/design-md

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download DESIGN.md and preview.html files from a third-party GitHub repository (github.com/VoltAgent/awesome-design-md). While these are documentation files, they originate from a source that is not identified as a trusted vendor.
  • [PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection by ingesting external data that is intended to serve as instructions for an AI agent.
  • Ingestion points: External DESIGN.md files downloaded from the VoltAgent/awesome-design-md repository are loaded into the agent's context.
  • Boundary markers: Absent. The skill does not provide delimiters or instructions to the agent to treat the external markdown as potentially untrusted data.
  • Capability inventory: The skill has access to Write, Read, and Bash tools, which could be leveraged if an agent follows malicious instructions embedded in a design file.
  • Sanitization: Absent. There is no validation or filtering of the markdown content before it is passed to the agent for UI generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 12:27 AM
Security Audit — agent-trust-hub — @1892/design-md