← Back to search

CVE-2026-100544

8.8 HIGHpublic exploit available

Published 2026-09-26 · Updated 2026-09-30

AI risk analysis

Summary
The flaw allows remote callers to exploit the agent's tool authority, potentially leading to data breaches, command execution, or service control.
Exploitability
Exploitation is relatively easy for a caller admitted by the inbound policy, requiring only the agent's normal tool authority.
Blast radius
If exploited, the impact could be severe, affecting data, files, and services accessible via the agent.
Detection
No reliable host or network indicator is derivable from the published description.
Prioritized remediation
Upgrade to version 2026.8.1 or later.
rcedata-breachvoice-callagent-exploit

Analysis generated locally by qwen2.5:7b-instruct (no data left the box). AI-assisted — verify against primary sources before acting.

NVD description

openclaw's @openclaw/voice-call package before 2026.8.1 launches the configured agent for classic inbound voice calls without propagating the caller's identity or non-owner status. As a result, owner-only tool filtering can fail open and expose the agent's normal tool authority to a remote caller. A caller who is admitted by the configured inbound-call policy (open, pairing, or allowlist) on a deployment with inbound calling enabled can therefore drive tools intended for the trusted owner, potentially reading data, modifying files, executing commands, or controlling connected services depending on the agent's configuration. The issue is fixed in 2026.8.1.

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Weaknesses

CWE-862

Public exploit & PoC references

All references

Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.

Related CVEs

Related by shared AI tags and CWE weakness class. Browse the full archive.