wordpress-plugin-core

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions and examples for integrating the Plugin Update Checker library (github.com/YahnisElsts/plugin-update-checker) and the Git Updater plugin for managing automatic updates from external repositories.
  • [EXTERNAL_DOWNLOADS]: The scripts/scaffold-plugin.sh script executes composer install to download dependencies when the PSR-4 architecture is selected, utilizing the official Composer registry.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for processing user-defined plugin requirements which could contain malicious instructions.
  • Ingestion points: User input provided to the agent describing plugin features or troubleshooting requests.
  • Boundary markers: The instructions do not explicitly define boundary markers to isolate user input from the skill's instructions.
  • Capability inventory: The agent can write files, create directories, and execute shell scripts (like scaffold-plugin.sh) which perform file modifications via sed.
  • Sanitization: The skill provides extensive instructions for sanitizing and escaping data within the generated plugin code to prevent XSS and SQLi, but does not specify sanitization for the prompt input itself.
  • [DYNAMIC_EXECUTION]: The scripts/scaffold-plugin.sh script uses sed to dynamically replace placeholders in template files based on user input during the scaffolding process, which is standard behavior for project initialization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 11:46 AM