meta-ad-scraper
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The script
scripts/search_meta_ads.pyuses the Pythonrequestslibrary to communicate withapi.apify.com. It performs POST and GET requests to trigger scraping tasks and retrieve dataset items from theapify/facebook-ads-scraperactor. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted data from an external source.
- Ingestion points: External ad data (text, titles, and descriptions) is fetched from the Meta Ad Library via Apify in
scripts/search_meta_ads.py. - Boundary markers: The output is printed as raw JSON or a formatted summary without specific delimiters or instructions to the agent to ignore embedded commands.
- Capability inventory: The script itself performs network requests via
requestsbut does not include local file-write or subprocess execution capabilities. However, the data it returns is intended for further processing by an agent. - Sanitization: The script does not perform sanitization or filtering of the scraped ad content before outputting it.
Audit Metadata