design-md

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to clone an external repository (https://github.com/voltagent/awesome-design-md.git) to access the design specifications required for its operation.
  • [COMMAND_EXECUTION]: The workflow defined in SKILL.md directs the agent to execute shell commands, specifically git clone, to fetch the design library if it is not found in common local paths.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because it processes data from an external source.
  • Ingestion points: The agent reads brand-specific documentation from <library>/design-md/<brand>/DESIGN.md as specified in the SKILL.md workflow.
  • Boundary markers: The skill lacks explicit boundary markers or instructions to ignore embedded commands within the ingested design files.
  • Capability inventory: The agent is instructed to "Follow it" and treat the design file as a "hard spec" for UI generation, potentially executing instructions embedded within the design documentation.
  • Sanitization: There is no evidence of sanitization or validation of the content fetched from the remote repository before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 10:01 AM
Security Audit — agent-trust-hub — design-md