kakao-bar-nearby

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches its full instructional logic and legal disclaimers at runtime using the @nomadamas/k-skill package via the npx utility.
  • [REMOTE_CODE_EXECUTION]: The SKILL.md file instructs the agent to execute shell commands (e.g., npx -y @nomadamas/k-skill@0 instruct kakao-bar-nearby) to obtain primary instructions, which allows the vendor to supply or update logic dynamically.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external Kakao Map place pages to extract venue-specific information such as seating and menus.
  • Ingestion points: External URLs (place.map.kakao.com) identified in the search results.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are used when browsing and extracting data from external sites.
  • Capability inventory: The skill can execute shell commands and perform network operations via a vendor-controlled proxy.
  • Sanitization: The instructions focus on field extraction but do not specify sanitization or validation of the ingested HTML content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:50 AM
Security Audit — agent-trust-hub — kakao-bar-nearby