highway-traffic-status

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions recommend using npx to download and run @nomadamas/k-skill, a package maintained by the skill's author, to manage instructions and script execution.
  • [COMMAND_EXECUTION]: Execution of the helper script scripts/highway_traffic.py is performed through shell commands to retrieve and process traffic data.
  • [PROMPT_INJECTION]: The skill processes data from external APIs (data.ex.co.kr and its.go.kr), which presents a surface for indirect prompt injection.
  • Ingestion points: Real-time traffic and CCTV metadata are retrieved via HTTP GET requests in scripts/highway_traffic.py.
  • Boundary markers: The skill outputs structured JSON or summary text; no explicit delimiters or instructions to ignore embedded content are used in the script's output.
  • Capability inventory: The helper script has the ability to make network requests and read from the ~/.config/k-skill/ directory.
  • Sanitization: The script parses responses using standard JSON and XML libraries, extracting only expected fields.
  • [SAFE]: No malicious patterns such as obfuscation, persistence mechanisms, or unauthorized privilege escalation were identified. Access to the configuration file is restricted to a skill-specific directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 10:19 AM
Security Audit — agent-trust-hub — highway-traffic-status