slack

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly asks the user to paste their Slack Bot OAuth token into the conversation and to run a command embedding that token (ruby ... save_token.rb 'PASTED_TOKEN'), which requires the LLM to receive and include the secret verbatim.

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly fetches and displays user-generated Slack content (e.g., scripts/messages.rb using conversations.history, scripts/search_messages.rb using /search.messages, and pins.rb using /pins.list) as part of the required SKILL.md Flow (Step 2: Read messages / Search messages), so untrusted third-party messages in the workspace could contain instructions that influence the agent's subsequent actions.