The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and processing various project files which could potentially contain malicious instructions designed to influence the agent's behavior during the migration process.
Ingestion points: The skill scans package.json, capacitor.config.ts, source code files (TypeScript/JavaScript), and multiple CI/CD configuration files (GitHub Actions, GitLab CI, Bitrise, etc.).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the content of these files as untrusted or to ignore any embedded natural language instructions.
Capability inventory: The agent is instructed to perform impactful actions based on the parsed data, including installing/uninstalling packages, rewriting imports and method calls in source files, and executing CLI commands.
Sanitization: No sanitization or validation steps are defined for the content extracted from the project files before it is used to generate code or execute commands.
[COMMAND_EXECUTION]: The skill frequently uses CLI tools to interact with the project and cloud services.
Evidence: Commands include npx @capawesome/cli for authentication, application management, channel creation, and signing key generation. It also uses npx cap sync to synchronize the Capacitor project and npm install/uninstall for package management.
[EXTERNAL_DOWNLOADS]: The skill retrieves and installs external code and configuration.
Evidence: The skill installs the @capawesome/capacitor-live-update and @capawesome/cli packages. It also provides a command to add an external MCP server from https://mcp.capawesome.io/mcp to provide documentation and management tools.

capgo-cloud-migration