Skill Manager

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

• Third-party content exposure detected (high risk: 0.90). The skill's Security Note in SKILL.md explicitly instructs use of npx clawhub which downloads and executes code from the public ClawHub registry, meaning untrusted third-party skill code is fetched and could influence agent behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill executes runtime npx commands ("npx clawhub install/update/info/uninstall") which download and run remote package code from the ClawHub/npm registry (e.g., https://www.npmjs.com/package/clawhub), so external code is fetched and executed as a required part of the workflow.