CVE-2026-35021

✕ Withdrawn — historical dataHIGHNVD 7.8Elevated
7.8CVSS
EchelonGraph verdictPlan mitigationSerious severity, but no confirmed exploitation yet.
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: <0.1%CVSS: 7.8Exploit: Elevated riskExposed services: Not assessed

No fix is confirmed yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for the fix.

Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the prompt editor invocation utility that allows attackers to execute arbitrary commands by crafting malicious file paths. Attackers can inject shell metacharacters such as $() or backtick expressions into file paths that are interpolated into shell commands executed via execSync. Although the file path is wrapped in double quotes, POSIX shell semantics (POSIX §2.2.3) do not prevent command substitution within double quotes, allowing injected expressions to be evaluated and resulting in arbitrary command execution with the privileges of the user running the CLI.

CVSS v3
7.8
EchelonGraph score
Not yet assessedThis CVE record was withdrawn by its numbering authority, so there is no vulnerability to rate.
EG Score
—
EG Risk
—
EPSS PROB
<0.1%
EPSS %ILE
12th
KEV
Not listed

Published

April 6, 2026

Last Modified

April 29, 2026

Advisory Details (2)

Auto-updated Apr 29, 2026
🔬 Proof of concept available. No fix on record yet.
generic

Anthropic Claude Code & Agent SDK OS Command Injection via promptEditor.ts | Advisories | VulnCheck

https://www.vulncheck.com/advisories/anthropic-claude-code-agent-sdk-os-command-injection-via-prompteditor-ts

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 0× in last 7d / 1× in last 30d)

Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.

  1. 2026-09-21 12:19 UTCOSV refresh
  2. 2026-09-02 09:44 UTCOSV refresh
  3. 2026-08-16 08:22 UTCGHSA enrichment
  4. 2026-08-12 19:44 UTCGHSA enrichment
  5. 2026-08-09 05:01 UTCGHSA enrichment
  6. 2026-08-06 00:06 UTCGHSA enrichment
  7. 2026-08-02 14:23 UTCEG score recompute
  8. 2026-08-02 14:23 UTCGHSA enrichment
  9. 2026-07-23 03:10 UTCEG score recompute▼ 7.80
  10. 2026-07-17 02:24 UTCOSV refresh
  11. 2026-06-11 21:33 UTCGHSA enrichment
  12. 2026-06-10 12:59 UTCGHSA enrichment
  13. 2026-06-10 01:28 UTCGHSA enrichment
  14. 2026-06-09 14:04 UTCGHSA enrichment
  15. 2026-06-08 09:16 UTCGHSA enrichment
  16. 2026-06-07 21:52 UTCGHSA enrichment
  17. 2026-06-07 10:27 UTCGHSA enrichment
  18. 2026-05-29 13:44 UTCEPSS rescore
  19. 2026-05-29 13:44 UTCEPSS rescore
  20. 2026-05-28 13:44 UTCEPSS rescore
  21. 2026-05-28 13:44 UTCEPSS rescore
  22. 2026-05-28 13:44 UTCEPSS rescore
  23. 2026-05-27 13:40 UTCEPSS rescore
  24. 2026-05-27 13:40 UTCEPSS rescore
  25. 2026-05-27 13:40 UTCEPSS rescore
Show 9 more
  1. 2026-05-26 13:44 UTCEPSS rescore
  2. 2026-05-26 07:18 UTCEPSS rescore
  3. 2026-05-26 07:18 UTCEPSS rescore
  4. 2026-05-20 22:38 UTCEPSS rescore
  5. 2026-05-20 22:38 UTCEPSS rescore
  6. 2026-05-20 18:51 UTCEG score recompute
  7. 2026-05-20 18:51 UTCGHSA enrichment
  8. 2026-05-20 11:22 UTCEPSS rescore
  9. 2026-05-20 11:22 UTCEPSS rescore

Frequently asked(5)

What is CVE-2026-35021?
CVE-2026-35021 is a high vulnerability published on April 6, 2026. Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the prompt editor invocation utility that allows attackers to execute arbitrary commands by crafting malicious file paths. Attackers can inject shell metacharacters such as $() or backtick expressions…
When was CVE-2026-35021 disclosed?
CVE-2026-35021 was first published on April 6, 2026, with the most recent update on April 29, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-35021 actively exploited?
CVE-2026-35021 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a <0.1% probability of exploitation in the next 30 days (12th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-35021?
CVE-2026-35021 has a CVSS v3 base score of 7.8 (NVD).
How do I remediate CVE-2026-35021?
No fix for CVE-2026-35021 is confirmed yet. Until one is published, restrict network exposure of the affected system or apply the vendor's mitigation — for example, keep it off the internet or limit it to trusted networks — and watch the vendor's advisory for the fix.

Dependency Blast Radius

Explore the affected products and dependency analysis for CVE-2026-35021

Explore →

Is Your Infrastructure Affected by CVE-2026-35021?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.