clawhub
Warn
Audited by Snyk on Mar 2, 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 instructs using the ClawHub CLI to search/install/update skills from the public registry https://clawdhub.com (e.g., "clawdhub install"/"update"/"search"), which pulls untrusted, user-published skill code that the agent would ingest and could change its behavior.
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 and installs agent skills at runtime from the default registry https://clawdhub.com, which can deliver remote code or prompt/instruction content that the agent will execute or use, so the registry URL is a runtime dependency controlling agent behavior.
Audit Metadata