The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx @useclawlink/cli to authenticate and interact with Apify resources, including running actors and retrieving datasets.
[EXTERNAL_DOWNLOADS]: The skill references the @useclawlink/cli package, which is fetched from the NPM registry. This is a standard dependency for the integration's functionality.
[REMOTE_CODE_EXECUTION]: The use of npx to run the @useclawlink/cli package involves downloading and executing code at runtime. As this is the official tool from the skill vendor, it is considered a legitimate operational requirement.
[INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest external data from web scrapers and datasets, creating a potential surface for indirect prompt injection.
Ingestion points: Results from apify_run_actor_sync, logs from apify_get_log, and items from apify_get_dataset_items.
Boundary markers: The instructions do not specify explicit delimiters or "ignore" warnings for the agent when processing retrieved content.
Capability inventory: The skill can execute shell commands via npx and perform network operations through the ClawLink service.
Sanitization: No evidence of data sanitization or schema validation is present in the skill's instructions.

apify