OpenClaw AI Agent Flaws Could Enable Prompt Injection and Data Exfiltration

2026-03-15T01:24:11Z0f9ff62b33658296b0cb29cf80803d822eb67398fb8be366ec2e042b96c195ad
ai-securityappamor/crackarmorbotnetbrowser-exploitcontainer-escapecredential-theftespionagelaw-enforcement-takedownn8nopen-vsxopenclawprivilege-escalationremote-code-executionsupply-chainveeamzero-day

What happened

A large set of high-impact incidents and vulnerabilities were reported: CNCERT warned that OpenClaw (self‑hosted AI agents) has weak defaults enabling prompt‑injection and data exfiltration; the GlassWorm campaign escalated supply‑chain abuse across the Open VSX registry using extensionPack/extensionDependencies; a suspected China‑linked espionage group targeted SE Asian militaries with AppleChris and MemFun malware; researchers disclosed multiple critical/actively exploited RCEs (notably n8n — CVE‑2025‑68613, CVE‑2026‑27577, CVE‑2026‑27493), Chrome zero‑days including CVE‑2026‑3909, and Veeam

Why it matters

A reviewed impact interpretation has not been published for this record.

Evidence and limitations

Source ID
the_hacker_news
Record identifier
0f9ff62b33658296b0cb29cf80803d822eb67398fb8be366ec2e042b96c195ad
Enrichment time
2026-03-15T01:24:11Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.