hankookilbo-news

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions suggest running npx -y @nomadamas/k-skill@0 to fetch and display the latest instructions. The package resides in the author's own namespace (@nomadamas), representing a vendor-owned resource for managing skill lifecycle.
  • [COMMAND_EXECUTION]: The skill uses curl to make POST requests to a remote news API and pipes the output into a short Python script for JSON parsing. The Python code is a standard one-liner (import json,sys; for i in json.load(sys.stdin)["result"]["structuredContent"]["items"]: print(...)) used solely for formatting metadata.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external news data (titles and excerpts) from https://mcp.hankookilbo.com/mcp.
  • Ingestion points: News metadata (titles, excerpts, and URLs) is retrieved via curl as specified in instruction.md.
  • Boundary markers: The skill includes instructions to strictly quote item.title without modification and use the [Title](URL) format to maintain data integrity.
  • Capability inventory: The skill uses curl for network access and python3 for parsing, but does not perform file writes or local execution based on the news content.
  • Sanitization: There is no active sanitization of the retrieved text; the skill relies on instructions for the agent to treat the metadata as literal citations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 04:29 AM
Security Audit — agent-trust-hub — hankookilbo-news