CVE-2026-51922
9.8 CRITICALpublic exploit availablePublished 2026-10-02 · Updated 2026-10-06
AI risk analysis
- Summary
- The flaw allows code injection in agentscope v1.0.20, enabling attackers to execute arbitrary commands, which can lead to full system compromise.
- Exploitability
- Exploitation is relatively straightforward given the code injection vulnerability, requiring an attacker to trigger the affected function.
- Blast radius
- If exploited, this can result in complete system compromise, data theft, and potential lateral movement within the network.
- Detection
- No reliable host or network indicator is derivable from the published description.
- Prioritized remediation
- Upgrade to agentscope v1.0.21 or later.
rcecode-injectioncommand-execution
Analysis generated locally by qwen2.5:7b-instruct (no data left the box). AI-assisted — verify against primary sources before acting.
NVD description
agentscope v1.0.20 contains code injection in execute_shell_command (src/agentscope/tool/_coding/_shell.py). Depending on the exposed entry, an attacker can trigger attacker-controlled code or command execution.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Weaknesses
CWE-94
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
- HIGHCVE-2024-42002PoC
- HIGHCVE-2026-100856PoC
- HIGHCVE-2026-103572
- CRITICALCVE-2026-105135PoC
- CRITICALCVE-2026-105903
- CRITICALCVE-2026-106621
- CRITICALCVE-2026-106624
- CRITICALCVE-2026-107700PoC
Related by shared AI tags and CWE weakness class. Browse the full archive.