slackcli

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

• Third-party content exposure detected (high risk: 0.75). The required workflow runs the installed slackcli to read Slack content (e.g., conversations read, search messages, canvas read), and those commands can ingest outsider-authored Slack message/canvas text into the agent’s LLM context via the CLI’s returned output.