apify-ecommerce
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions require the agent to execute a provided Node.js script (
run_actor.js) to interact with the Apify API. This script handles input parsing, API communication, and data formatting. - [EXTERNAL_DOWNLOADS]: The skill fetches dataset results from
api.apify.com. Apify is a well-known service for web scraping and automation, and the script uses its official API endpoints for its primary functionality. - [DATA_EXFILTRATION]: To function, the skill requires an
APIFY_TOKEN. The instructions correctly advise storing this sensitive credential in a.envfile rather than hardcoding it, which is consistent with secure development practices. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks because it processes untrusted data scraped from third-party e-commerce websites.
- Ingestion points: Data is fetched from external marketplaces via the Apify API and loaded into the agent's context for summarization.
- Boundary markers: No explicit delimiters are defined in the instructions to separate the scraped data from agent instructions.
- Capability inventory: The skill allows the agent to execute shell commands (running the Node.js script) and write files to the local disk.
- Sanitization: The provided script includes basic data formatting and truncation for display but does not sanitize the content for malicious prompt instructions.
Audit Metadata