competitor-analysis

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to scrape and process content from external websites (competitor homepages, pricing, and documentation). A third-party website could theoretically host content intended to influence the agent's summary or comparison logic.
  • Ingestion points: Scraped content from competitor URLs (homepage, pricing, features).
  • Boundary markers: The skill instructions do not explicitly define delimiters for untrusted content.
  • Capability inventory: The skill uses searching, scraping, and spawning worker agents to process data.
  • Sanitization: No specific sanitization methods for the ingested text are mentioned in the strategy.
  • [EXTERNAL_DOWNLOADS]: The skill performs search and scraping operations on external websites. References to well-known services like Vercel and Netlify are used as examples, which are considered safe sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 02:43 PM
Security Audit — agent-trust-hub — competitor-analysis