skills/min9lin9/k-skill/hwp/Gen Agent Trust Hub

hwp

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches its primary instructions and utility tools using npx -y @nomadamas/k-skill@0.- [COMMAND_EXECUTION]: Provides bash commands to run the kordoc CLI for document conversion, JSON extraction, and directory watching.- [DYNAMIC_EXECUTION]: Includes Node.js code blocks executed via heredocs (`node --input-type=module
  • <<'EOF') to demonstrate advanced document parsing, field extraction, and diffing via the kordoc` Node.js API.- [INDIRECT_PROMPT_INJECTION]: The skill parses external document files (HWP, HWPX, HWPML) which represents an attack surface for indirect instructions.
  • Ingestion points: Input files specified in instruction.md (e.g., 보고서.hwp, 검토서.hwpx).
  • Boundary markers: Not explicitly defined in the provided instructions.
  • Capability inventory: Shell command execution via kordoc CLI and file system writing using writeFileSync in instruction.md.
  • Sanitization: No specific sanitization or filtering of document content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 02:40 PM