apify-ultimate-scraper
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted data from external websites via Apify's API, creating a surface for indirect prompt injection.\n
- Ingestion points: External data is fetched from api.apify.com within reference/scripts/run_actor.js.\n
- Boundary markers: The script lacks delimiters or 'ignore' instructions to prevent the agent from obeying instructions in the scraped output.\n
- Capability inventory: The skill uses a Node.js script (reference/scripts/run_actor.js) and the mcpc tool to interact with web APIs and the local filesystem.\n
- Sanitization: Content is truncated for length in the displayQuickAnswer function, but no filtering or escaping is applied to the retrieved data.\n- [EXTERNAL_DOWNLOADS]: The skill instructions specify the installation of the @apify/mcpc tool from the official npm registry, which is a utility provided by a well-known service for Apify integration.\n- [COMMAND_EXECUTION]: The skill's workflow requires the agent to execute local shell commands and a Node.js script (reference/scripts/run_actor.js) to perform data extraction and management tasks.
Audit Metadata