meta-ad-scraper
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script
scripts/search_meta_ads.pydesigned to be executed via the CLI to automate search and retrieval of ad data. - [EXTERNAL_DOWNLOADS]: The script performs network operations using the
requestslibrary to connect to the official Apify API (api.apify.com) to run scraping actors and fetch results. Apify is a well-known service for web scraping and automation. - [CREDENTIALS_UNSAFE]: The skill requires an
APIFY_API_TOKENfor operation. While it correctly suggests using an environment variable, it also allows providing the token as a CLI flag, which may be captured in system logs or process lists. - [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting untrusted data (advertisement text and titles) from Facebook and Instagram. 1. Ingestion points: Ad creative text and metadata fetched from Apify in
scripts/search_meta_ads.py. 2. Boundary markers: Absent; the script returns the raw or truncated text directly from the source. 3. Capability inventory: Usesrequestsfor network communication with Apify. 4. Sanitization: No validation or sanitization is performed on the scraped content before output.
Audit Metadata