always-design-system

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a developer guideline designed to maintain design consistency and code quality.
  • [COMMAND_EXECUTION]: The skill uses bash to perform directory listings (ls) of local documentation and components. This is used for project exploration and does not involve risky or obfuscated commands.
  • [PROMPT_INJECTION]: The skill employs strong instructional language to enforce technical constraints on code generation. This is a standard practice for engineering prompts and does not target the safety guardrails of the underlying model.
  • [DATA_EXFILTRATION]: No network activity or patterns suggesting data exfiltration were found. The tool access is limited to the local filesystem for project maintenance tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 11:58 AM
Security Audit — agent-trust-hub — always-design-system