clawhub

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). This SKILL.md explicitly instructs fetching and installing skills from the public ClawHub registry (default https://clawhub.com) via commands like "clawhub install" and "clawhub update", which ingests untrusted third‑party skill code that can change the agent's behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The ClawHub CLI uses the default registry URL https://clawhub.com at runtime to fetch and install remote skills (via commands like "clawhub install"), which means external code from that URL can be retrieved and executed and thus can directly control agent behavior.