CVE-2026-96620
waiting for further signalsZero needs more public information before it can validate it.GHSA-h4mw-j7qp-8mwm ↗EUVD-2026-103155 ↗
description
Versions of the Python claude-agent-sdk before 0.2.121 mishandle values used to resume sessions. An attacker may cause commands to run outside the SDK's intended permission checks if an application passes attacker-controlled input as the resume session identifier.
mitigation
Upgrade claude-agent-sdk to version 0.2.121 or later. Until upgraded, do not use untrusted input to select or construct resume session identifiers.
fixed in 0.2.121
outcome
Contextual: an exploit technique exists, but no deterministic check could cover this one.
source signals
Public signals that triggered or updated the pipeline. These are inputs for the deltas above.
- 2026-10-16 19:44Zghsa: trigger signal, started the run
- 2026-10-16 19:44Zcve.org record for CVE-2026-96620
this entry in the feed
GET /api/v1/feed/CVE-2026-96620
{ "etk_id": "ETK-2026-1808", "cve_id": "CVE-2026-96620", "display_id": "CVE-2026-96620", "ghsa_id": "GHSA-h4mw-j7qp-8mwm", "euvd_id": "EUVD-2026-103155", "status": "published", "anchor_state": "anchored", "title": "Command argument injection in claude-agent-sdk resume handling", "summary": "Versions of the Python claude-agent-sdk before 0.2.121 mishandle values used to resume sessions. An attacker may cause commands to run outside the SDK's intended permission checks if an application passes attacker-controlled input as the resume session identifier.", "mitigation": "Upgrade claude-agent-sdk to version 0.2.121 or later. Until upgraded, do not use untrusted input to select or construct resume session identifiers.", "vendor": "pip", "product": "pip:claude-agent-sdk", "affected": [ { "affected_notes": [], "affected_ranges": [ "< 0.2.121" ], "ecosystem": "pip", "fixed_versions": [ "0.2.121" ], "package_name": "claude-agent-sdk", "purl": "pkg:pypi/claude-agent-sdk" } ], "cwes": null, "cvss_score": 9.2, "cvss_src": "cna_vendor", "cvss_vector": "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", "epss_score": 0.0058, "epss_percentile": 0.4655, "epss_asof": "2026-10-20", "automation": "contextual", "check": false, "check_confidence_basis": null, "exploit": false, "pipeline_minutes": 13.496065466666666, "t0_at": "2026-10-16T19:44:01.260000+00:00", "signals": { "trigger_signal": { "at": "2026-10-16T19:44:01.260000+00:00", "days": 0, "is_lower_bound": false, "measured_at": "2026-10-16T19:44:01.260000+00:00", "url": "https://github.com/advisories/GHSA-h4mw-j7qp-8mwm" } } }
published 2026-10-16 20:36Z
last change 2026-10-21 04:45Z
Need the technical details behind an entry?
Every entry here shows what we attempted and when. The technical details, the generated exploit that fired it and the evidence behind the verdict are not public. Tell us about your use case and we’ll get back to you about extended API access.