competitor-profiling
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its web-scraping functionality.\n
- Ingestion points: Content is fetched from external competitor URLs via the firecrawl_scrape and firecrawl_crawl tools.\n
- Boundary markers: The instructions lack explicit delimiters or guidance to ignore instructions embedded within the scraped content during the synthesis phase.\n
- Capability inventory: The agent has the ability to write to the local file system (competitor-profiles directory) and perform network requests via integrated tools.\n
- Sanitization: No validation or filtering of the untrusted web content is implemented before it is processed by the model.\n- [EXTERNAL_DOWNLOADS]: The skill uses Firecrawl and DataForSEO services to fetch website content and SEO analytics data from external domains.
Audit Metadata