skills/simota/agent-skills/vitrine/Gen Agent Trust Hub

vitrine

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of component source code to generate documentation and automated stories. This represents a functional surface for indirect prompt injection inherent to code-analysis tools.
  • Ingestion points: The skill analyzes application source files (including .tsx, .vue, and .svelte) during its creation and audit modes as defined in SKILL.md.
  • Boundary markers: The instructions do not include specific delimiters or 'ignore' warnings for the analyzed code content, which is typical for this class of development utility.
  • Capability inventory: The skill can execute shell commands via package managers (e.g., pnpm, npx) and perform file system operations to create documentation and story files (SKILL.md, reference/visual-regression.md).
  • Sanitization: No specific code-sanitization or validation procedures are detailed for the ingested source materials before processing.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of numerous third-party Storybook addons and developer tools via official package registries. These references target well-known organizations and technology providers (e.g., Chromatic, Axe-core, React Cosmos, Playwright) and are documented neutrally.
  • [COMMAND_EXECUTION]: Instructions throughout the skill involve the execution of common CLI utilities for building, serving, and testing component libraries in a development environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:03 PM