BREW-RAWDOG-CVE-2026-42203 (GHSA-XQMJ-J6MV-4862)
Vulnerability from osv_homebrew – Published: 2026-08-13 17:32 – Updated: 2026-11-14 09:29 – Source websiteImpact
The POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process.
The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could reach it. Depending on how the proxy is deployed, this could expose secrets in the process environment (such as provider API keys or database credentials) and allow commands to be run on the host.
Proxy deployments running an affected version are in scope.
Patches
The issue is fixed in 1.83.7-stable. The fix switches the prompt template renderer to a sandboxed environment that blocks the attributes this attack relies on.
LiteLLM recommends upgrading to 1.83.7-stable or later.
Workarounds
If upgrading is not immediately possible:
- Block
POST /prompts/testat your reverse proxy or API gateway. - Review and rotate API keys that should not have access to prompt management routes.
{
"affected": [
{
"ecosystem_specific": {
"fix": "bump",
"range_state": "fixed",
"resource": "litellm",
"resource_purl": "pkg:pypi/litellm@1.109.0",
"upstream_fixed_in": "1.83.7"
},
"package": {
"ecosystem": "Homebrew",
"name": "rawdog",
"purl": "pkg:brew/rawdog"
},
"ranges": [
{
"events": [
{
"introduced": "0.1.6_17"
},
{
"fixed": "0.1.6_22"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"database_specific": {
"confidence": "high",
"source": "matched",
"strategy": "registry",
"upstream_evidence": [
{
"ecosystem": "PyPI",
"key": "pkg:pypi/litellm@1.109.0",
"name": "litellm",
"resource": "litellm",
"strategy": "registry",
"subject_version": "1.109.0"
}
]
},
"details": "### Impact\nThe `POST /prompts/test` endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process.\n\nThe endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could reach it. Depending on how the proxy is deployed, this could expose secrets in the process environment (such as provider API keys or database credentials) and allow commands to be run on the host.\n\nProxy deployments running an affected version are in scope.\n\n### Patches\nThe issue is fixed in **`1.83.7-stable`**. The fix switches the prompt template renderer to a sandboxed environment that blocks the attributes this attack relies on.\n\nLiteLLM recommends upgrading to `1.83.7-stable` or later.\n\n### Workarounds\nIf upgrading is not immediately possible:\n\n1. Block `POST /prompts/test` at your reverse proxy or API gateway.\n2. Review and rotate API keys that should not have access to prompt management routes.",
"id": "BREW-rawdog-CVE-2026-42203",
"modified": "2026-11-14T09:29:03Z",
"published": "2026-08-13T17:32:08Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/BerriAI/litellm/security/advisories/GHSA-xqmj-j6mv-4862"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-42203"
},
{
"type": "PACKAGE",
"url": "https://github.com/BerriAI/litellm"
},
{
"type": "WEB",
"url": "https://github.com/BerriAI/litellm/releases/tag/v1.83.7-stable"
}
],
"schema_version": "1.7.3",
"severity": [
{
"score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
"type": "CVSS_V4"
}
],
"summary": "LiteLLM: Server-Side Template Injection in /prompts/test endpoint",
"upstream": [
"GHSA-xqmj-j6mv-4862",
"CVE-2026-42203",
"PYSEC-2026-2602"
]
}
Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.
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.
Vulnerability timeline
Sightings and recorded dates, grouped by day · UTC
How durations are calculated
Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.
Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.
Loading timeline…
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.