Skills
Navigate
skills/tomevault-io/skills-registry/ux-design-expert/Gen Agent Trust Hub

ux-design-expert

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill constructs shell commands by interpolating user queries into an echo statement piped to spice sql. This pattern introduces a risk of shell command injection if the AI agent does not escape shell metacharacters (such as backticks, semicolons, or pipes) in the user-provided natural language input.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface through its retrieval-augmented workflow.
  • Ingestion points: Data is retrieved from the ux_design_spec dataset via the spice sql command in SKILL.md.
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded instructions within the retrieved dataset content.
  • Capability inventory: The skill has shell execution capabilities via the spice CLI tool.
  • Sanitization: No sanitization or validation of the retrieved content is performed before it is synthesized into agent responses.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 01:18 AM
Security Audit — agent-trust-hub — ux-design-expert