gongsijiga-search

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx -y @nomadamas/k-skill@0 to fetch its primary instructions and update its components. These resources originate from the vendor's own package repository.
  • [COMMAND_EXECUTION]: The skill instructs the agent to run shell commands including npm install gongsijiga-search and node -e to execute its core functionality. These are standard operations for a developer-oriented library.
  • [DYNAMIC_EXECUTION]: The lookup logic is executed via node -e, which dynamically runs JavaScript code to invoke the lookupGongsijiga function.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data.
  • Ingestion points: User-supplied address strings and HTTP response data from the realtyprice.kr domain.
  • Boundary markers: None explicitly defined in the provided instructions.
  • Capability inventory: Subprocess execution via npm and node, and network access via curl or HTTP libraries.
  • Sanitization: Not explicitly documented in the provided markdown instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:49 AM
Security Audit — agent-trust-hub — gongsijiga-search