web-scraper-agent

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes examples that embed API keys/tokens directly into code and construct Authorization headers (e.g., ApifyClient("your-token"), FirecrawlApp(api_key="your-key"), Authorization: f"Bearer {gemini_key}"), which would require the LLM to place secret values verbatim into generated requests or code.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text can be ingested when the agent scrapes arbitrary runtime URLs (public web pages) and then passes extracted HTML/content into the LLM for “AI enrichment” / Firecrawl extraction (e.g., app.extract(..., prompt=...) and the LLM enrichment step using scraped Data).