skills/pixel-vibe/skills/pixel/Gen Agent Trust Hub

pixel

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill package contains only Markdown documentation and instructional references; no executable scripts, binaries, or source code are provided within the skill files themselves.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it instructs the agent to process data from external sources, specifically Figma design context and user prompts.
  • Ingestion points: Figma design data and visual references extracted via the get_design_context and get_screenshot MCP tools as described in SKILL.md.
  • Boundary markers: Absent; the instructions do not provide specific delimiters or ignore-behavior rules for the agent when interpreting instructions that might be embedded in the design metadata or descriptions.
  • Capability inventory: The agent is tasked with generating functional Vue 3 and Nuxt component code, which is a significant capability if the agent is influenced by malicious design data.
  • Sanitization: Absent; the skill lacks specific steps for validating or filtering content retrieved from the Figma API before it is used to generate code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 07:57 AM