Prompt-Injection Vulnerability Found in Agentic AI App Manus

Security researchers identified a prompt-injection vulnerability in the agentic AI application Manus, valued at $4B, showing how attacker-supplied external data could manipulate the AI's behavior.

Disclosed 24 September 2026 · Record updated 1 October 2026

Impact

A prompt-injection bug was found in the Manus agentic AI app, highlighting risks from insufficient security filtering of external data inputs.

Our coverage

A puppet master's strings lead through an open window, where invisible hands pull a mechanical automaton away from its intended path toward hidden cliffs.

Vulnerabilities

Prompt-injection flaw reported in $4B agentic AI app Manus

Security researchers say attacker-supplied external data could steer the agent's behaviour, according to a report published on 24 September 2026.

24 Sept 2026

Sources

darkreading.comhttps://darkreading.com/application-security/prompt-injection-bug-agentic-ai-app-manus