capacitor-plugin-generator

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard CLI tools to automate the development workflow, including initialization with @capacitor/create-plugin, dependency installation via npm install, and platform verification using gradlew and swift build.
  • [EXTERNAL_DOWNLOADS]: Fetches configuration and project templates from the ionic-team's official GitHub repositories and established package registries like npm.
  • [PROMPT_INJECTION]: The skill processes user-defined requirements via conversational input or the references/input-contract.md file to generate code. It mitigates indirect injection risks by establishing a mandatory evidence chain:
  • Ingestion points: Reads structured YAML from references/input-contract.md (Category 8 surface).
  • Boundary markers: Explicitly defines a schema and validation rules for the input contract in the instructions.
  • Capability inventory: Restricts operations to building and local verification of the plugin scaffold using standard development tools.
  • Sanitization: Instructs the agent to validate input against the schema and halt if specific blockers or high-complexity hooks are detected in the metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 07:44 PM
Security Audit — agent-trust-hub — capacitor-plugin-generator