skills/bklit/bklit-ui/bklit-studio/Gen Agent Trust Hub

bklit-studio

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill content is strictly instructional, providing a roadmap for developers to build and edit charts within a specific monorepo environment. It does not contain malicious instructions, obfuscation, or unauthorized data access patterns.
  • [COMMAND_EXECUTION]: The instructions include standard development commands such as pnpm dev to start a local server. These are routine operations for a developer tool and are directed at the local repository root.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing chart data and configurations.
  • Ingestion points: Data enters the system via URL states (?chart=<slug>) and configuration files in packages/studio/src/lib/.
  • Boundary markers: The skill references specific parsers in packages/studio/src/lib/studio-parsers.ts to manage state.
  • Capability inventory: The skill facilitates local file edits in packages/studio and packages/ui and previewing them in a local browser.
  • Sanitization: Implementation details point toward structured state management and specific render helpers in registry.tsx to handle property interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 08:23 PM