yebigun-training

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches its primary instructions and helper utilities by running npx -y @nomadamas/k-skill@0, which downloads code from the NPM registry. This package is a vendor resource owned by the skill author.
  • [REMOTE_CODE_EXECUTION]: The use of npx allows for the runtime execution of external code to ensure the agent uses the most up-to-date instructions and automation logic.
  • [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands to manage a Chrome browser instance via its remote debugging port and to run local Node.js extraction scripts.
  • [DATA_EXFILTRATION]: The skill reads sensitive military service and training records from the yebigun1.mil.kr portal. While instructions specify that data should only be stored in a local cache directory, the agent possesses the capability to access and process this personal information.
  • [SAFE]: No unauthorized persistence, privilege escalation, or malicious obfuscation was detected. The ingestion of external web content from the government training portal is evaluated as follows: (1) Ingestion points: yebigun1.mil.kr pages; (2) Boundary markers: Absent; (3) Capability inventory: Shell execution and local file writing; (4) Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 02:27 AM
Security Audit — agent-trust-hub — yebigun-training