agent-slack

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

• Third-party content exposure detected (medium risk: 0.30). The skill implements a Slack CLI wrapper that reads messages, channel history, search results, and threads from Slack, which are outsider-authored chat and communication feeds.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installation via curl | sh from an external GitHub repository, constituting an unverified runtime external dependency.