Lack of Sufficient Guardrails Lead to Excessive Agency (LLM08) in Some LLM Applications

ronjor · Nov 25, 2025 at 11:34 AM

Original Release Date: 2025-11-24 | Last Revised: 2025-11-24

Overview
Retell AI's API creates AI voice agents that have excessive permissions and functionality, as a result of insufficient amounts of guardrails. As a result, attackers can exploit this and conduct large scale social engineering, phishing, and misinformation campaigns.
Click to expand...

Solution
Retell AI has not released a statement, and coordinated disclosure was attempted. Users should be aware and follow security best practices when speaking to an AI voice agent and avoid sensitive data input. Developers should limit functionality and permissions through instating sufficient guardrails and implement manual human approval for high-risk or high volume tasks
Click to expand...

Log in or Sign up

Lack of Sufficient Guardrails Lead to Excessive Agency (LLM08) in Some LLM Applications

ronjor Global Moderator

Log in or Sign up

Lack of Sufficient Guardrails Lead to Excessive Agency (LLM08) in Some LLM Applications

ronjor Global Moderator

Useful Searches