ai-api-integrations
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: 0.90). The skill explicitly exposes web access via the Claude Agent SDK built-in tools ("WebSearch", "WebFetch") and mentions "web/X search" for Grok, meaning the agent can fetch and ingest open/public web and social content which it will read and interpret as part of its workflow.
Audit Metadata