Hackers Can Turn AI Workflows Into Privileged Data-Stealing Proxies Without Jailbreaking Models
Noma Labs describes Workflow Identity Hijacking, where unauthenticated external requesters abuse AI workflows' privileged service accounts to exfiltrate internal data without prompt injection.
Noma Labs identified 'Workflow Identity Hijacking,' an authorization gap in enterprise AI workflows triggered via public inboxes, web forms, GitHub issues, and support systems. Attackers submit legitimate-looking requests that cause workflows to retrieve and disclose internal data using privileged service accounts or creator credentials, without any prompt injection or model misbehavior. Defenses include propagating requester identity through workflows, short-lived scoped tokens, and access-control checks before sensitive actions.
- Unauthenticated requesters can trigger workflows with excessive privileges
- Model guardrails miss the issue because requests appear benign
- Scheduled workflows remain exposed to untrusted inputs like inboxes
- Treat LLM outputs as untrusted data with separate access-control checks
- Separate sensitive retrieval from automated external responses
From the original article
3 min read at cybersecuritynews.com
Enterprise AI workflows can be vulnerable to misuse that exposes sensitive information without prompt injection, account compromise, or jailbreaking a large language model. This vulnerability, termed Workflow Identity Hijacking, exploits authorization gaps between external requesters and the privileged identities used by AI automation.
By Abinaya · cybersecuritynews.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.