baoyu-comic

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it transforms untrusted user-provided text into narrative outlines and detailed image generation prompts.\n
  • Ingestion points: User-provided markdown files or text input used as the source for comic creation.\n
  • Boundary markers: The skill relies on natural language structure rather than strict adversarial boundary markers to isolate user-provided content from generation instructions.\n
  • Capability inventory: The skill can read/write local files and execute shell commands to run generation scripts and PDF utilities.\n
  • Sanitization: Source content is analyzed and summarized by the agent, but no explicit sanitization is performed to filter out potentially malicious instructions embedded in the source text.\n- [COMMAND_EXECUTION]: The skill executes local scripts and sibling skill resources to complete the comic workflow.\n
  • It runs scripts/merge-to-pdf.ts using the Bun runtime to compile images into a PDF.\n
  • It invokes a sibling skill baoyu-image-gen via shell commands to generate character sheets and comic pages. These are vendor-owned resources and part of the expected functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 09:52 AM