discord-reader

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads and ingests user-generated Discord content via opencli (see SKILL.md Steps 3–4 and references/commands.md using opencli discord-app read / search), then summarizes and uses that content for financial research, so arbitrary third-party messages can materially influence agent decisions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires installing and running the opencli package (https://github.com/jackwener/opencli) via npm/npx as a required runtime dependency, which fetches remote code that will be executed locally—constituting a clear remote-code execution dependency.