read-slack-messages

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

• Third-party content exposure detected (high risk: 0.95). Outsider-authored free text from Slack messages is fetched at runtime via Slack API calls (conversations.history, conversations.replies, search.messages) and then JSON-printed as text/matches[].text into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The README includes setup commands that fetch-and-execute remote installers (curl -fsSL https://bun.sh/install | bash and irm bun.sh/install.ps1 | iex which loads bun.sh/install.ps1), so the skill's setup requires executing remote code from https://bun.sh/install.