The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from several sources which could potentially contain malicious instructions intended to influence agent behavior.
Ingestion points: The skill reads local project files like manifest.json and package.json and fetches remote guidance from github.com/Esri/arcgis-experience-builder-sdk-resources.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present when processing these inputs.
Capability inventory: The skill is instructed to execute shell commands via npm, pnpm, and custom build/test scripts defined in the workspace.
Sanitization: There is no evidence of sanitization or strict schema validation for the ingested text before it is processed.
[EXTERNAL_DOWNLOADS]: Fetches workflow references and implementation guidance from Esri's official GitHub repository.
[COMMAND_EXECUTION]: Directs the agent to execute environment startup, dependency installation, and production build scripts based on the local installation's configuration.

exb-widget