slack-automate

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

• Third-party content exposure detected (high risk: 0.95). Slack message bodies and thread replies returned by the official Slack MCP tools (e.g., mcp__slack__search_messages, mcp__slack__read_channel, mcp__slack__read_thread) are outsider-authored free text from other Slack users, which the workflow formats into Markdown and thus feeds into the agent’s LLM context.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)