skills/okooo5km/skills4u/zipic/Gen Agent Trust Hub

zipic

Pass

Audited by Gen Agent Trust Hub on Oct 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to invoke the zipic CLI tool to perform image compression, conversion, and optimization tasks (e.g., zipic compress --json ...). It also uses local shell and PowerShell scripts (scripts/detect.sh, scripts/detect.ps1) to verify the execution environment and locate the application binaries. \n- [EXTERNAL_DOWNLOADS]: The instructions reference the official Zipic website (https://zipic.app) for application downloads and troubleshooting resources. It also mentions using standard package managers like Homebrew on macOS for installation. \n- [INDIRECT_PROMPT_INJECTION]: The skill features a documentation retrieval mechanism where it encourages the agent to fetch live markdown content from the vendor's official domains (docs.zipic.app, zipic.app/llms.txt) to answer user queries regarding pricing, features, and troubleshooting. \n
  • Ingestion points: External documentation fetched from https://docs.zipic.app/ and https://zipic.app/llms.txt (documented in reference/resources.md).\n
  • Boundary markers: None explicitly defined for the fetched content.\n
  • Capability inventory: Includes execution of the local zipic CLI, shell/PowerShell scripts for environment detection, and file system writes for compressed images.\n
  • Sanitization: No specific sanitization methods are described for the fetched documentation content. \n- [DYNAMIC_EXECUTION]: The skill provides a pre-defined PowerShell script block used to bridge WSL environments to the native Windows application by executing commands through the powershell.exe interop layer.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 18, 2026, 06:22 PM