CVE Intelligence
Critical Input validation

CVE-2026-96620 — Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution

Claude Agent SDK is a Python SDK for Claude Code. Prior to 0.2.121, the resume option is passed to the Claude CLI as a separate token without validation, so a dash-leading value is parsed as an independent CLI flag. An attacker can inject the --mcp-config flag to define a stdio MCP server, causing arbitrary command execution at CLI startup outside the SDK permission controls. The issue is exploitable when an application passes untrusted input as the session ID to resume. This issue is fixed in version 0.2.121.

Published Oct 16, 2026 · Updated Oct 16, 2026 · Sources: CVE Program (cve.org) e CISA ADP, NIST National Vulnerability Database, GitHub Security Advisories · CNA: GitHub_M

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.
How the score was calculated
  • Technical severity (critical)+10

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation
Not confirmed
Not in CISA KEV — an absence of record, not proof it is unexploited.
EPSS FIRST
—
No EPSS score.
Affects
Anthropics
Claude-agent-sdk-python and 1 more
CVSS base
9.2
Critical · 2 source(s)

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

  • Pip Claude-agent-sdk: fixed in version 0.2.121 — github.com (GitHub Security Advisories)

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

  1. Identify exposed assets running the affected vendor/product/version combinations (Anthropics Claude-agent-sdk-python, Pip Claude-agent-sdk).
  2. The attack is network-based and needs no privileges: restrict exposure (ACLs, VPN, WAF) until patched.
  3. Apply the fixed version or the patch documented under Remediation.
  4. Search available logs for exploit probes matching the vulnerability class (input validation), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

VendorProductVersionsStatusSource
Anthropics Claude-agent-sdk-python version < 0.2.121 Vulnerable CVE Program (cve.org) e CISA ADP
Pip Claude-agent-sdk < 0.2.121 Vulnerable GitHub Security Advisories

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector
Network
Attack complexity
Low
Attack requirements
Present
Privileges required
None
User interaction
None
Scope
X
Confidentiality (vulnerable system)
High
Integrity (vulnerable system)
High
Availability (vulnerable system)
High
Confidentiality (subsequent)
None
Integrity (subsequent)
None
Availability (subsequent)
None

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

ScoreVersionSeverityExpl.ImpactScored by
9.2 CVSS 4.0 Critical — — security-advisories@github.com via NIST National Vulnerability Database
9.2 CVSS 4.0 Critical — — GitHub_M via CVE Program (cve.org) e CISA ADP
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X (score shown at the top: security-advisories@github.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-20 · Improper Input Validation

Other CVEs with this weakness →

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

  • Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
web/proxy/WAF logsnetwork IDS/IPS

Timeline

What happened to this CVE, newest first.

  • 2026
  • Fix documented
    Oct 16, 2026 · GitHub Security Advisories
  • Affected products added · pip/claude-agent-sdk
    Oct 16, 2026 · GitHub Security Advisories
  • Source status changed · Published → Received
    Oct 16, 2026 · NIST National Vulnerability Database
  • Record published
    Oct 16, 2026
  • CVSS changed · 9.2
    Oct 16, 2026 · CVE Program (cve.org) e CISA ADP
  • Source status changed · → Published
    Oct 16, 2026 · CVE Program (cve.org) e CISA ADP
  • Record created in this database
    Oct 16, 2026 · CVE Program (cve.org) e CISA ADP
  • CVE published
    Oct 16, 2026 · GitHub_M

Source activity

Repeated readings are counted rather than listed.

  • 1× References added · Oct 16, 2026 – Oct 16, 2026
  • 1× Official description updated · Oct 16, 2026 – Oct 16, 2026

References

5 on the record

Elsewhere on this site

Anthropics
every CVE for this vendor
Input validation
same class
CWE-20
other pages naming this weakness

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

  • No FIRST EPSS score.
  • No CISA SSVC assessment.
  • No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
  • No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
  • No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-96620 is "Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution", rated Critical. It affects Claude-agent-sdk-python (Anthropics); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 9.2 describes technical severity. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.

Sign in or create an account to comment and suggest corrections.