openclaw-config
Warn
Audited by Snyk on Mar 7, 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.md explicitly describes installing and loading third-party skills from ClawdHub/GitHub and lists Social/Web skills (e.g., bird, blogwatcher) that ingest public social/web content and "load[ ] into context when relevant," meaning the agent fetches and interprets untrusted user-generated web/social content that can change its behavior.
Audit Metadata