gas-slack-bot

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to capture and write Slack tokens, verification tokens, deployment IDs, and other secrets into .env and Script Properties ("record unique values ... including Slack IDs, tokens ... add it to .env"), which requires handling and outputting secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests outsider-authored free text from Slack events: doPost(e) parses the incoming JSON payload (parseJsonBody_ → payload.event.text) and then uses that text (normalizeText_) to generate the bot reply, so any non-user Slack message content becomes LLM-context input via the agent’s Slack interaction loop.