The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted content from external websites.
Ingestion points: Data enters the agent context via tools like apify_get_dataset_items and apify_get_record which fetch scraped content.
Boundary markers: No specific delimiters or instructions to ignore embedded commands were found in the provided documentation.
Capability inventory: The skill possesses the ability to create webhooks (apify_create_webhook), manage schedules (apify_create_schedule), and write data (apify_push_dataset_items), which could be targeted by an injection attack.
Sanitization: No evidence of sanitization or filtering of external content is mentioned.
[DATA_EXFILTRATION]: The skill includes functionality to create and manage webhooks via apify_create_webhook. While this is a standard feature of the Apify platform, it provides a mechanism for sending scraping results or other data to external URLs. Users should monitor which URLs the agent configures as webhook destinations.

apify-scraping