claude-design-system-architect

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and processing untrusted data from external sources.
  • Ingestion points: The skill uses the WebFetch tool to analyze existing websites and accepts user-provided brand briefs as the primary input for design generation (SKILL.md).
  • Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore potential malicious instructions embedded within the fetched web content or brand briefs.
  • Capability inventory: The skill is authorized to use Bash, Write, and Agent tools (SKILL.md frontmatter). If manipulated by malicious instructions in the fetched data, these tools could be used to perform unintended file operations or execute shell commands.
  • Sanitization: There is no evidence of sanitization, filtering, or validation performed on the data retrieved from external URLs before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 08:32 PM
Security Audit — agent-trust-hub — claude-design-system-architect