apify-ultimate-scraper

Pass

Audited by Gen Agent Trust Hub on Nov 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to scrape data from untrusted external sources (social media, websites, reviews) and provides workflows for feeding this data into AI models for analysis, which presents an indirect prompt injection surface.
  • Ingestion points: Data is ingested from various third-party platforms including Instagram, Facebook, TikTok, and general web crawls as described in SKILL.md and the references/workflows/ directory.
  • Boundary markers: The instructions do not define or require the use of delimiters (e.g., XML tags or triple backticks) or "ignore instructions" headers when processing the scraped content with AI nodes.
  • Capability inventory: The skill uses the Apify CLI to execute remote tasks, fetch datasets, and write results to the local filesystem using standard file tools.
  • Sanitization: There is no mention of sanitizing, filtering, or escaping the retrieved data to prevent malicious payloads embedded in the scraped content from influencing the agent's logic or downstream AI processing.
  • [COMMAND_EXECUTION]: The skill extensively uses the apify CLI to perform searches (apify actors search), fetch schemas (apify actors info), and execute remote scraping tasks (apify actors call, apify actors start). These commands are essential for the skill's intended purpose and are restricted to the Apify platform's ecosystem.
  • [EXTERNAL_DOWNLOADS]: The skill requires the user to install the apify-cli via npm (npm install -g apify-cli). This is a prerequisite for interacting with the vendor's platform and is a standard dependency for this type of tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 18, 2026, 05:50 PM