daangn-realty-search

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions utilize npx to execute the @nomadamas/k-skill package. This package is managed by the skill's author and is used to provide instructions and updates.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external real estate listing data from realty.daangn.com, presenting a potential surface for indirect prompt injection.\n
  • Ingestion points: Data is retrieved in scripts/daangn_realty.py and scripts/daangn_detail_ld.py.\n
  • Boundary markers: There are no explicit markers to delimit the retrieved listing content.\n
  • Capability inventory: The skill is limited to performing network requests to specific realty domains and outputting JSON to the console. It lacks the ability to write to the filesystem or execute commands based on external data.\n
  • Sanitization: External content is serialized into JSON format before display.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:36 AM