autogpt-agents
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: 1.00). The skill includes HTTP request blocks, webhook handlers, and integrations with Discord/Notion/GitHub plus explicit "Web" browsing/interaction and marketplace features, which let agents fetch and process arbitrary public or user-generated content (webpages, social posts, webhook payloads), exposing the agent to untrusted third-party content.
Audit Metadata