The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and modify user-provided source files and project configuration to perform integration tasks. This creates a vulnerability surface where malicious code or comments within those files could attempt to influence the agent's behavior.
Ingestion points: User-provided JavaScript/TypeScript source files (e.g., www/index.js), config.xml, and package.json (as described in references/integration.md and references/migration.md).
Boundary markers: None identified; instructions do not specify the use of delimiters or warnings to ignore embedded instructions in processed data.
Capability inventory: The skill uses file-editing tools to modify user code in place and executes shell commands (cordova plugin add, cordova prepare).
Sanitization: No sanitization or validation of the ingested code content is described.
[EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and install official Scandit Cordova plugins from public registries. These resources are provided by the skill's author and are standard for the described integration workflow.
[COMMAND_EXECUTION]: The skill uses the cordova command-line interface to manage plugins and synchronize native artifacts. These operations are standard development practices for Cordova projects.

sparkscan-cordova