ai-engineer

Warn

Audited by Snyk on Feb 19, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly lists "Document processing: PDF extraction, web scraping, API integrations" and "Tool integration: web search" and even includes the example "Build an AI agent that can browse the web and perform research tasks," which shows the agent is expected to fetch and read untrusted public web content (third‑party pages) that can materially influence its actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 04:10 AM