apify-content-analytics

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @apify/mcpc tool via npm and interacts with legitimate Apify service domains. These resources originate from a well-known service provider.\n- [COMMAND_EXECUTION]: The workflow involves running a Node.js script (run_actor.js) that performs network requests to the Apify API and saves scraping results to local files in CSV or JSON format. This functionality is consistent with the skill's stated purpose.\n- [DATA_EXFILTRATION]: The skill retrieves the APIFY_TOKEN from a .env file to authenticate requests to api.apify.com. This is a standard and safe method for managing API credentials.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface when processing data from external social media platforms.\n
  • Ingestion points: Untrusted content is fetched from api.apify.com dataset items within the reference/scripts/run_actor.js script.\n
  • Boundary markers: The script output uses simple text separators but lacks explicit delimiters or instructions to the agent to ignore any embedded commands within the content.\n
  • Capability inventory: The agent has the ability to execute further commands and write to the filesystem across various scripts, which could be misdirected if malicious instructions are present in the scraped data.\n
  • Sanitization: The script truncates long fields but does not sanitize the content for injection markers or escape special characters before displaying them in the chat.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 11:41 AM