clawdhub-hardened

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to search, install, and update agent skills from the public registry https://clawdhub.com (and allows overriding the registry), which means it fetches and ingests third‑party skill packages that the agent would incorporate and that could materially change behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs the agent to fetch and install remote skills at runtime from the default registry https://clawdhub.com, which delivers code (skills) that will be installed/executed and can directly control agent prompts or behavior.