scrape
Warn
Audited by Snyk on Mar 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to call Scrapling MCP tools to fetch/scrape arbitrary public URLs (e.g., "/scrape https://example.com/blog/ai-trends", bulk competitor pages, or protected sites) and then read, summarize, store, and act on the extracted content, which exposes it to untrusted third-party web content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill calls Scrapling MCP at runtime to fetch arbitrary user-supplied pages (e.g., https://example.com/blog/ai-trends) and injects the scraped content into the agent's processing/summaries, so remote pages can directly control model prompts/outputs.
Audit Metadata