ionic-app-upgrades
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage packages and build the application. Evidence includes commands like 'npm install', 'npm run build', 'npx cap sync', and 'react-scripts test' found in SKILL.md and reference files. These are standard operations for migrating and verifying a web or mobile project's dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data which could technically contain malicious instructions, though this is a standard risk for development tools. 1. Ingestion points: Reads package.json and project source code to identify versions and apply migration patterns (mentioned in SKILL.md). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are provided in the skill instructions. 3. Capability inventory: The skill has the ability to execute package installation and build scripts via npm and npx (found in SKILL.md, upgrade-v4-to-v5.md, etc.). 4. Sanitization: No sanitization of the content from package.json or project files is performed before processing.
Audit Metadata