product-hunt-scraper

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the orth command-line utility to interact with the startup-launches and company-intel services. This tool is used to fetch data and enrich it with intelligence results.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from Product Hunt, creating a surface for indirect prompt injection.
  • Ingestion points: External product names, domains, and taglines are retrieved from the Product Hunt source in Step 1.
  • Boundary markers: No specific delimiters or "ignore instructions" markers are defined to wrap the external content.
  • Capability inventory: The agent uses orth to perform network operations and data enrichment, and is instructed to answer analytical questions about the fetched data.
  • Sanitization: There is no explicit logic to sanitize or validate the <product_name> or <product_domain> variables before they are interpolated into the shell command in Step 2.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 05:39 AM
Security Audit — agent-trust-hub — product-hunt-scraper