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

pixel

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The references/setup.md file contains instructions to install the @mekari/pixel3 package using pnpm. This is a routine operation for setting up the required design system library from a recognized vendor.
  • [PROMPT_INJECTION]: The workflow involves ingesting external design data from Figma using the get_design_context tool. While this is the intended purpose of the skill, it introduces an indirect prompt injection surface where instructions hidden in Figma designs could influence code generation.
  • Ingestion points: External Figma node data accessed via get_design_context (SKILL.md).
  • Boundary markers: No specific delimiters or "ignore instructions" markers are defined for the design data in the prompts.
  • Capability inventory: Generates Vue/Nuxt source code based on ingested data.
  • Sanitization: No sanitization or validation of the ingested design data is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 06:08 PM
Security Audit — agent-trust-hub — pixel