ux-designer

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is configured to analyze untrusted external data, which creates a potential vector for indirect instructions.\n
  • Ingestion points: Processes data from URLs and local file paths passed as arguments through tools like WebFetch and Read (SKILL.md).\n
  • Boundary markers: The instructions lack explicit delimiters or specific warnings to the agent to disregard embedded instructions within the fetched data.\n
  • Capability inventory: The skill includes Bash in its allowed tools list, which allows for shell command execution that could be exploited if malicious instructions in external data are processed.\n
  • Sanitization: No evidence of content validation or sanitization was found in the analysis of the skill's instructions or logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 12:36 PM
Security Audit — agent-trust-hub — ux-designer