AIA-002 Slack AI data exfiltration via indirect prompt injection, per PromptArmor

ID: AIA-002
Category: AI AI agent incident
Disclosed: 2024-08
Systems: Slack AI
Harm type: Data leak / prompt injection
Status: reported
Reported by the source; no vendor confirmation recorded in seed data.

Summary

PromptArmor showed that instructions planted in a public channel could make Slack AI return data from private channels inside a crafted link.

Controls

Controls that could prevent, detect, or support recovery from this kind of failure. Mappings are editorial judgments made by the method, not findings about what any party should have done.

NIST AI RMF

MEASURE 2.7 Security and resilience are evaluated and documented
MAP 4.1 Risks from third-party components are mapped

NIST SP 800-53

AC-4 Information Flow Enforcement
SI-10 Information Input Validation
SC-7 Boundary Protection

Human-approval (JCR) checkpoint

not applicable

Sources

promptarmor.substack.com primary link checked 2026-10-31, HTTP 200
Post dated Aug 20, 2024
https://promptarmor.substack.com/p/data-exfiltration-from-slack-ai-via

Corrections

2026-10-28 Verification round 1: date month and summary verified against the PromptArmor post (Aug 20, 2024).

To report an error in this entry, see corrections.