BREW-SUMMARIZE-CVE-2026-45244 (CVE-2026-45244)
Vulnerability from osv_homebrew – Published: 2026-08-13 17:41 – Updated: 2026-09-16 10:35 – Source websiteSummarize prior to 0.15.1 contains a missing authorization vulnerability that allows attackers to execute browser automation actions without per-call user approval when the extension automation feature is enabled. Attackers can influence the agent through malicious page or summary content to invoke enabled extension automation tools such as navigation or debugger-backed actions, bypassing the final user approval step when a user interacts with attacker-controlled content.
{
"affected": [
{
"ecosystem_specific": {
"fix": "bump",
"range_state": "fixed",
"upstream_fixed_in": "0.15.0"
},
"package": {
"ecosystem": "Homebrew",
"name": "summarize",
"purl": "pkg:brew/summarize"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "0.21.11"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"database_specific": {
"confidence": "high",
"source": "matched",
"strategy": "git",
"upstream_evidence": [
{
"ecosystem": "GIT",
"key": "https://github.com/steipete/summarize",
"name": "https://github.com/steipete/summarize",
"strategy": "git",
"subject_version": "0.22.0"
},
{
"ecosystem": "npm",
"key": "pkg:npm/%40steipete/summarize@0.22.0",
"name": "@steipete/summarize",
"strategy": "registry",
"subject_version": "0.22.0"
}
]
},
"details": "Summarize prior to 0.15.1 contains a missing authorization vulnerability that allows attackers to execute browser automation actions without per-call user approval when the extension automation feature is enabled. Attackers can influence the agent through malicious page or summary content to invoke enabled extension automation tools such as navigation or debugger-backed actions, bypassing the final user approval step when a user interacts with attacker-controlled content.",
"id": "BREW-summarize-CVE-2026-45244",
"modified": "2026-09-16T10:35:17Z",
"published": "2026-08-13T17:41:25Z",
"references": [
{
"type": "ADVISORY",
"url": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/45xxx/CVE-2026-45244.json"
},
{
"type": "ADVISORY",
"url": "https://github.com/steipete/summarize/releases/tag/v0.15.2"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-45244"
},
{
"type": "ADVISORY",
"url": "https://www.vulncheck.com/advisories/summarize-unapproved-browser-automation-execution"
},
{
"type": "REPORT",
"url": "https://github.com/steipete/summarize/pull/219"
},
{
"type": "FIX",
"url": "https://github.com/steipete/summarize/commit/e64fe3ecd1bb4fdc181dcfa88c96b9e1914ced0e"
},
{
"type": "PACKAGE",
"url": "https://github.com/steipete/summarize"
}
],
"schema_version": "1.7.3",
"severity": [
{
"score": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:A/VC:N/VI:N/VA:N/SC:L/SI:L/SA:N",
"type": "CVSS_V4"
}
],
"summary": "Summarize \u003c 0.15.1 Unapproved Browser Automation Execution",
"upstream": [
"CVE-2026-45244",
"GHSA-67gq-6q8c-qqh6"
]
}
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.