The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The scripts apify_leads_sheet.py and enrich_leads.py access a sensitive file named service_account.json to authenticate with Google Cloud services. This file typically contains private keys that grant access to the user's Google Sheets data.
[DATA_EXFILTRATION]: The skill performs network requests to Apify and Google APIs to transmit search queries and receive scraped business details. These operations are essential for the skill's functionality and target well-known, trusted services.
[PROMPT_INJECTION]: The skill processes untrusted data scraped from external websites and Google Maps listings, which presents an indirect prompt injection surface. This data is written to Google Sheets without extensive sanitization.
Ingestion points: Scraped business data and contact information are retrieved from Apify datasets in apify_leads_sheet.py and enrich_leads.py.
Boundary markers: No explicit delimiters or instructions are used to separate scraped content from the processing logic.
Capability inventory: The skill can execute remote scraping tasks via Apify and perform write operations to external spreadsheets.
Sanitization: Apart from basic URL parsing in apify_leads_sheet.py, no significant sanitization of the scraped text content is performed before it is stored.

apify-google-maps