korean-spell-check

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill transmits user-supplied text or file contents to the external domain https://nara-speller.co.kr for grammar checking.
  • [COMMAND_EXECUTION]: The instructions contain an inline Python script that the agent is expected to run, utilizing the urllib library for network communication and re for parsing results.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user input or local files which could contain malicious instructions. Evidence Chain: 1. Ingestion points: User-provided text and local Markdown/text files. 2. Boundary markers: None present. 3. Capability inventory: Network access and file read access. 4. Sanitization: None present.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:41 PM
Security Audit — agent-trust-hub — korean-spell-check