apify-booking-host-leads

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes instructions to use the "apify actors call" command via the CLI, which executes shell commands to interact with the Apify platform to run various scraping actors.
  • [EXTERNAL_DOWNLOADS]: The workflow relies on calling remote actors from the Apify registry, including official packages such as "apify/google-search-scraper" and community-maintained ones like "voyager/booking-scraper", "lukaskrivka/google-maps-with-contact-details", and "vdrmota/contact-info-scraper".
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and processing untrusted data from external websites and search results.
  • Ingestion points: External data collected from Booking.com search results and website scraping tools.
  • Boundary markers: Absent; there are no instructions to the agent to treat scraped data as untrusted or to use delimiters to separate data from instructions.
  • Capability inventory: The skill triggers subprocess calls via the Apify CLI as documented in SKILL.md.
  • Sanitization: No sanitization or content validation is specified before the agent processes the scraped data or passes it to further steps in the waterfall.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 08:11 PM
Security Audit — agent-trust-hub — apify-booking-host-leads