apify-ultimate-scraper

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill metadata specifies the installation of the @apify/mcpc package via Node.js. This package provides the CLI tool used for actor discovery and schema fetching.
  • [COMMAND_EXECUTION]: The skill executes shell commands using the mcpc CLI and a local Node.js script (reference/scripts/run_actor.js). The local script includes specific validation functions (validateActorId, validateJsonInput, validateOutputPath) to ensure that inputs do not contain malicious characters and that file operations are restricted to the current working directory.
  • [INDIRECT_PROMPT_INJECTION]: As a web scraping tool, the skill ingests data from external sources (social media platforms, search engines) that could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: The run_actor.js script fetches dataset items from the Apify API (https://api.apify.com/v2/datasets/).
  • Boundary markers: The skill instructs the agent to select actors and run scripts but does not explicitly define delimiters for the ingested web content when displaying summaries.
  • Capability inventory: The skill has the ability to make network requests to Apify services and write results to the local filesystem.
  • Sanitization: The execution script performs data truncation and CSV escaping on the fetched results before writing or displaying them.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 11:31 PM
Security Audit — agent-trust-hub — apify-ultimate-scraper