delivery-tracking

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes curl and python3 as subprocesses to fetch and parse parcel tracking data from official websites. This is a standard and expected behavior for the stated functionality.
  • [EXTERNAL_DOWNLOADS]: Communicates with the official domains of CJ Logistics (cjlogistics.com) and Korea Post (epost.go.kr). These are well-known, legitimate services for logistics tracking.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: No sensitive data access or unauthorized exfiltration was detected. The skill only processes parcel invoice numbers provided by the user.
  • [PROMPT_INJECTION]: No evidence of prompt injection, instruction overrides, or safety filter bypass attempts was found.
  • [INDIRECT_PROMPT_INJECTION]: While the skill ingests external data from web pages, it uses strict regex-based and JSON-path parsing to extract specific fields rather than passing raw content to the agent, which effectively mitigates injection risks from the carrier responses.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 03:00 PM