LangChain: Path traversal and sandbox escape in LangChain file-search middleware and loaders
LangChain is a framework for building agents and LLM-powered applications. Prior to 1.3.9, several LangChain components that resolve filesystem paths or expand search patterns do not consistently confine the resolved path to the intended root directory. Affected behaviors include: a file-search agent middleware that validates a starting directory but not the search pattern or the resolved target of matched files, so glob patterns and symlinks can reach files outside the configured root; prompt- and chain/agent-configuration loaders that accept path fields and resolve them without confining the result to a trusted base or rejecting symlink targets; and path-prefix authorization checks that compare by string prefix without a path-segment boundary, so a sibling path sharing the prefix is accepted. When these components receive path values, search patterns, or workspace contents influenced by an untrusted source — including an LLM acting on untrusted input — the result can be disclosure of files outside the intended boundary. This vulnerability is fixed in 1.3.9.
Noroxi analysis
No Noroxi analysis for this record yet
We don't hand-write analysis for the hundreds of thousands of vulnerabilities in the database; that wouldn't be honest. For notable, high-impact vulnerabilities our team writes the mechanism, detection and remediation steps.
We use this product, ask for help- Published
- Jun 22, 2026
- Updated
- Jun 26, 2026
- EPSS
- 0.2% · 10th percentile
- CWE
- CWE-22
Sign in to follow · You’ll be notified if a followed record enters KEV, gets an exploit or is updated.
Report tools
Action score
22
Monitor
Low priority for now.
- CVSS
- 22 / 40 · 5.5 / 10
- CISA KEV
- 0 / 30 · Not listed
- EPSS
- 0 / 30 · 0.2%
CISA SSVC decision
- Exploitation
- none
- Automatable
- no
- Technical impact
- partial
Vulnrichment: CISA's decision-tree inputs.
CNA vs NVD score
- NVD
- 5.5
- CNA · GitHub_M
- 5.1
- 0.4 point gap
CVSS:3.1/AV:L/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N
The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.
Affected systems
| Vendor | Product | CPE |
|---|---|---|
| langchain | langchain | cpe:2.3:a:langchain:langchain |
Affected versions
NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.
- langchain langchainbefore 1.3.9
Versions reported by the vendor
Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.
langchain-ai langchain
- < 1.3.9affected
langchain-ai langchain-anthropic
- < 1.4.6affected
Package-level exposure
OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.
| Ecosystem | Package | Affected range | Fix |
|---|---|---|---|
| PyPI | langchain | before 1.3.9 | 1.3.9 |
| PyPI | langchain-anthropic | before 1.4.6 | 1.4.6 |
Same product
langchain: all recordsOther highest-scoring records for the same primary product.
- CVE-2023-29374In LangChain through 0.0.131, the LLMMathChain chain allows prompt injection attacks that can execute arbitrary code via the Python exec met51Plan
- CVE-2023-46229LangChain before 0.0.317 allows SSRF via document_loaders/recursive_url_loader.py because crawling can proceed from an external server to an48Plan
- CVE-2025-2828SSRF Vulnerability in RequestsToolkit in langchain-ai/langchain46Plan
- CVE-2024-8309SQL Injection in langchain-ai/langchain43Plan
- CVE-2023-36281An issue in langchain v.0.0.171 allows a remote attacker to execute arbitrary code via a JSON file to load_prompt.40Plan
- CVE-2023-38896An issue in Harrison Chase langchain v.0.0.194 and before allows a remote attacker to execute arbitrary code via the from_math_prompt and fr40Plan
Remediation
Which version to upgrade to
Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.
| Product / package | Fixed version | Source |
|---|---|---|
| langchain-ai langchain | 1.3.9 · description | Vendor (CNA) |
| PyPI:langchain | 1.3.9 | Package registry (OSV) |
| PyPI:langchain-anthropic | 1.4.6 | Package registry (OSV) |
Exploit status
No known public exploit
No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.
Research context
For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.
Timeline
From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.
No dated events beyond publication.
FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).
Patch and commit links
Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.
Credits
All researchersFinders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.
No credits in the CNA record.
Variant candidates
Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.
No nightly-computed relations.
Chain candidates
An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.
—
Bug bounty scope
No known public program.
Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).
Technical details
Attack conditions
- Someone with local access to the system can trigger it.
- A low-privileged account is enough.
- No user action is required.
- No special conditions are required; it is repeatable.
If successful
- Confidentiality
- high · data can be read
- Integrity
- none
- Availability
- none
- Attack vector
- Local
- Attack complexity
- Low
- Privileges required
- Low
- User interaction
- None
- Scope
- Unchanged
- Confidentiality impact
- High
- Integrity impact
- None
- Availability impact
- None
Weakness class (CWE)
CWE-22 · Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')CVSS vector
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
nvd-primary
Root cause
A user-supplied file name is joined with the allowed directory, but the result is never checked to confirm it is still inside that directory.
The bug in code
The whole CWE-22 classA representative example of this vulnerability class. Not the vendor's source code; it shows the faulty pattern and its fix.
Vulnerable
const file = path.join(ROOT, req.query.name);res.sendFile(file);Fixed
const file = path.resolve(ROOT, req.query.name);if (!file.startsWith(ROOT + path.sep)) { return res.sendStatus(400);}res.sendFile(file);Attack context
MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.
Attack patterns (CAPEC)
- Path TraversalCAPEC-126likelihood: High · Very High
- Using Slashes and URL Encoding Combined to Bypass Validation LogicCAPEC-64likelihood: High · High
- Manipulating Web Input to File System CallsCAPEC-76likelihood: High · Very High
- Using Escaped Slashes in Alternate EncodingCAPEC-78likelihood: High · High
- Using Slashes in Alternate EncodingCAPEC-79likelihood: High · High
ATT&CK techniques
—
Change log
- Fix✗ → ✓
For records you follow, these changes also arrive as notifications. →
References
- github.com/langchain-ai/langchain/commit/dcaf7795a3e6590af55c3ff7bda6add6355e9ea6
- github.com/langchain-ai/langchain/security/advisories/GHSA-gr75-jv2w-4656
Vendor advisories and official records. Exploit/PoC links are deliberately left out.