baoyu-comic

Pass

Audited by Gen Agent Trust Hub on May 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to resolve the bun runtime environment if it is not already present on the system. Both are well-known development tools.
  • [COMMAND_EXECUTION]: Executes local TypeScript scripts (scripts/merge-to-pdf.ts) using the Bun runtime to combine generated images into a single PDF document.
  • [COMMAND_EXECUTION]: Uses system utilities such as sips (macOS native) or pngquant for image compression and format conversion tasks.
  • [COMMAND_EXECUTION]: Dynamically discovers and executes a sibling wrapper script (baoyu-codex-imagegen/src/main.ts) through directory traversal to facilitate integration with optional image generation backends.
  • [PROMPT_INJECTION]: The skill processes arbitrary user-provided text to generate comics, which creates a surface for indirect prompt injection.
  • Ingestion points: User-supplied source content or files (e.g., source.md).
  • Boundary markers: Not explicitly defined in the provided prompt templates (references/base-prompt.md).
  • Capability inventory: Local script execution (scripts/merge-to-pdf.ts), system utility calls (sips, pngquant), and invocation of external image generation tools.
  • Sanitization: No specific content filtering or sanitization logic is implemented in the provided scripts.
  • [SAFE]: Manages user preferences and watermark settings through local configuration files (EXTEND.md) stored in project-specific or user-home directories.
Audit Metadata
Risk Level
SAFE
Analyzed
May 29, 2026, 04:36 AM
Security Audit — agent-trust-hub — baoyu-comic