openclaw-marketing-skills

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

• Third-party content exposure detected (medium risk: 0.30). The workflow incorporates the x-twitter-connect skill via TweetClaw, which monitors and searches external X/Twitter conversations containing untrusted outsider-authored posts and replies.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill documentation instructs downloading and installing packages from GitHub and ClawHub repositories (e.g., LeoYeAI/openclaw-marketing-skills and Xquik-dev/tweetclaw), which constitute runtime external operational dependencies with common/reputable unofficial provenance.