design-md

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions and examples for downloading external design specifications from a remote repository using command-line tools.
  • Evidence: curl -O https://raw.githubusercontent.com/VoltAgent/awesome-design-md/main/design-md/linear/DESIGN.md in SKILL.md.
  • Context: The skill points to a collection of 58+ files in the VoltAgent/awesome-design-md repository. These files are downloaded without checksums or integrity verification.
  • [INDIRECT_PROMPT_INJECTION]: The primary function of this skill is to have an AI agent ingest and follow instructions from a DESIGN.md file, which may originate from an untrusted remote source.
  • Ingestion points: The agent is explicitly told to read the DESIGN.md file placed in the project root (SKILL.md).
  • Boundary markers: The instructions do not specify the use of delimiters or specific system prompts to prevent the agent from obeying malicious instructions embedded within the design file.
  • Capability inventory: The agent uses the content to generate code and UI components, providing a path for injected instructions to influence the agent's output.
  • Sanitization: No sanitization or content validation steps are described for the external markdown files before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:52 AM
Security Audit — agent-trust-hub — design-md