clawhub
Warn
Audited by Snyk on Feb 15, 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 clawhub CLI explicitly fetches and installs skills from the public registry (default https://clawhub.com and optionally any --registry/CLAWHUB_REGISTRY), which lets the agent download and execute arbitrary third-party/user-published skill content, exposing it to untrusted indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The ClawHub CLI explicitly fetches skills at runtime from the default registry https://clawhub.com (used by install/update commands), which would deliver remote skill code or prompts that the agent would execute or follow, so this external URL is a required runtime dependency that can directly control agent behavior.
Audit Metadata