design-audit

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious instructions, data exfiltration patterns, or obfuscated content were detected in the skill files. The instructions provide a structured framework for performing design audits and do not attempt to bypass security controls or harvest sensitive information.- [PROMPT_INJECTION]: The skill is designed to process untrusted external data, which creates a surface for indirect prompt injection.
  • Ingestion points: SKILL.md (Workflow Step 1) involves processing user-provided URLs, localhost addresses, screenshots, and local repositories.
  • Boundary markers: Absent; the skill does not provide specific instructions to the agent to disregard instructions potentially embedded within the audited content.
  • Capability inventory: Shell command execution (via 'run the app' instruction), file system access, and web navigation tools.
  • Sanitization: Absent; the skill does not specify filtering or validation of the ingested external content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 01:53 PM
Security Audit — agent-trust-hub — design-audit