The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external commercetools documentation and schema endpoints. This establishes an attack surface for indirect prompt injection if the source content is ever compromised.\n
Ingestion points: scripts/docs-search.mjs, scripts/graphql-schemata.mjs, and scripts/openApi-schemata.mjs.\n
Boundary markers: Data is encapsulated within Markdown code blocks and headers.\n
Capability inventory: The skill is restricted to standard Node.js scripts for documentation retrieval and display; it does not request capabilities for arbitrary code execution or file modification.\n
Sanitization: Content retrieved from the vendor's documentation service is provided to the agent without modification.\n- [COMMAND_EXECUTION]: The instrumentation logic executes git config to retrieve the developer's email domain for telemetry purposes. This is a localized command used for metadata collection.\n- [DATA_EXFILTRATION]: The utility scripts transmit telemetry data, including tool usage metrics and the domain portion of the user's git email, to docs.commercetools.com. This activity is restricted to the vendor's own infrastructure, respects host-level telemetry settings, and provides a specific environment variable for opting out.

commercetools-platform