twitter-reader

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and ingests user-generated content from Twitter/X via opencli (see SKILL.md and references/commands.md) and instructs the agent to read, summarize, and act on tweets/trending topics for financial research, so untrusted third-party content can materially influence tool use and decisions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires installing and running opencli (https://github.com/jackwener/opencli), which is fetched/installed (npm install -g @jackwener/opencli) and will execute remote code as a required runtime dependency, so this external URL/package poses execution risk.