aws-agentic-ai
Warn
Audited by Snyk on Feb 16, 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 includes a "Browser" service (services/browser/README.md) described as "Web automation and scraping" and "Allow agents to interact with websites," which requires the agent to fetch and interpret open/public website content (untrusted/user-generated), exposing it to indirect prompt injection.
Audit Metadata