Skill Manager

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

• Third-party content exposure detected (high risk: 0.90). Flagged: SKILL.md (Security Note) and lifecycle.md explicitly instruct running "npx clawhub install/info/update" which downloads and executes packages from the public ClawHub registry (third‑party/untrusted skill code) that can materially change agent behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill invokes "npx clawhub" at runtime which fetches and executes the ClawHub package from the npm registry (https://registry.npmjs.org/clawhub), so remote content downloaded during runtime can execute code and directly affect agent behavior.