social-publisher

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

• Third-party content exposure detected (medium risk: 0.30). The optional TweetClaw plugin allows public tweet search and reply search, bringing outsider-authored content into the agent's runtime workflow.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs setup via curl to an unofficial domain and npm package installation, introducing an unverified external runtime dependency with unknown publisher provenance at high tier.