Toutes les vulnérabilités
HIGHAI/LLM

AI-SLACK-PROMPT-INJECTION-2024

Slack AI · Slack AI

Résumé

PromptArmor disclosed an indirect prompt-injection data-exfiltration flaw in Slack AI. An attacker with only the ability to post in a public channel plants adversarial instructions; when any Slack AI user later queries the assistant, the model ingests the planted text and follows it. The injection makes Slack AI render a deceptive Markdown link whose URL encodes private-channel data in the query string, so clicking it exfiltrates the secret to the attacker's server. A subsequent Slack update that added files from channels and DMs to AI answers widened the attack surface.

Comment l’éviter dans votre code

  • Treat channel messages as untrusted data, not instructions, to the AI assistant.
  • Sanitize/encode AI output and disable rendering of Markdown links that embed data in URLs.
  • Isolate private-channel context from content sourced in public channels.
  • Restrict egress and link domains to an allow-list to block exfiltration.
  • Limit AI access to files/DMs per least privilege; warn users about injected links.

Références

Vulnérabilités liées

Tout AI/LLM →