ionic-enterprise-sdk-migration

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes several command-line tools to inspect and modify the project environment.
  • A Node.js script is used to read and filter the package.json file for relevant dependencies.
  • The ripgrep (rg) utility is used to search for plugin usage within the project's source code.
  • Package managers (npm) and Capacitor CLI (npx cap) are used for installation, uninstallation, and project synchronization.
  • [EXTERNAL_DOWNLOADS]: The skill manages the installation of several external plugins from the @capgo and @capacitor scopes.
  • These downloads target the official npm registry for well-known and vendor-owned packages.
  • It also references the net.zetetic:sqlcipher-android library for implementing encrypted storage.
  • [INDIRECT_PROMPT_INJECTION]: The skill's migration logic is based on reading project files such as source code and metadata.
  • Ingestion points: The agent reads package.json and project source files to identify migration targets (specifically @ionic-enterprise/ packages).
  • Boundary markers: The inspection logic is specifically targeted at identifying plugin strings, and the skill provides clear instructions on what should be treated as project data.
  • Capability inventory: The skill has the ability to execute shell commands (npm, node, rg) and modify project files, which are standard for migration tasks.
  • Sanitization: The risk is minimal as the commands are scoped to identification and standard package management tasks with no evidence of unsafe interpolation.
  • [DATA_EXPOSURE_EXFILTRATION]: The skill includes specific instructions to protect sensitive data during the migration process.
  • It explicitly directs the agent to omit secrets from reports during project inspection.
  • It provides guidance on avoiding hardcoded encryption keys, suggesting they be stored in secure biometric vaults instead of JavaScript constants.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 12:05 AM