AGENT LAB: SKILLS

payload

Warn

Audited by Snyk on Feb 17, 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 explicitly instructs the agent to fetch and read public third-party URLs (e.g., "When users need detailed type information, fetch these URLs" and links to payloadcms.com and GitHub in the Resources/Type References), so it expects the agent to ingest untrusted open-web content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 10:22 PM