meta-ad-scraper
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the Meta Ad Library (such as ad creative text and descriptions) and presents it to the agent, creating a surface for indirect prompt injection.
- Ingestion points: The script
scripts/search_meta_ads.pyfetches ad datasets from the Apify API. - Boundary markers: The output is provided as raw JSON or a formatted summary without explicit boundary markers or instructions to the agent to disregard potential commands within the scraped data.
- Capability inventory: The skill has the capability to perform network requests (via the
requestslibrary) and execute local Python scripts. - Sanitization: The script does not perform sanitization, filtering, or escaping of the content retrieved from the external Meta Ad Library before displaying it to the agent.
- [COMMAND_EXECUTION]: The skill functions by executing a local Python script (
scripts/search_meta_ads.py) to interact with external APIs. - [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to install the
requestslibrary from the official Python Package Index (PyPI).
Audit Metadata