GHSA-v8hw-mh8c-jxfc CVE-2026-33873 PYSEC-2026-82
Langflow has Authenticated Code Execution in Agentic Assistant Validation
- Severity
- 0.0 / 10
- Critical · CVSS 4.0
- Exploit chance (EPSS)
- 1.45%
- Chance of exploitation in the next 30 days. Higher than 73.40% of scored vulnerabilities.
- Known exploited
- No
- Not in CISA's catalog
- Weakness
- CWE-94 Improper Control of Generation of Code ('Code Injection')
- Fix
1.9.0- Upgrade langflow to this version or later
Description
Description
1. Summary
The Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the implementation reaches dynamic execution sinks and instantiates the generated class server-side.
In deployments where an attacker can access the Agentic Assistant feature and influence the model output, this can result in arbitrary server-side Python execution.
2. Description
2.1 Intended Functionality
The Agentic Assistant endpoints are designed to help users generate and validate components for a flow. Users can submit requests to the assistant, which returns candidate component code for further processing.
A reasonable security expectation is that validation should treat model output as untrusted text and perform only static or side-effect-free checks.
The externally reachable endpoints are:
The request model accepts attacker-influenceable fields such as input_value, flow_id, provider, model_name, session_id, and max_retries:
2.2 Root Cause
In the affected code path, Langflow processes model output through the following chain:
/assist
→ execute_flow_with_validation()
→ execute_flow_file()
→ LLM returns component code
→ extract_component_code()
→ validate_component_code()
→ create_class()
→ generated class is instantiated
The assistant service reaches the validation path here:
The code extraction step occurs here:
The validation entry point is here:
The issue is that this validation path is not purely static. It ultimately invokes create_class() in lfx.custom.validate, where Python code is dynamically executed via exec(...), including both global-scope preparation and class construction.
As a result, LLM-generated code is treated as executable Python rather than inert data. This means the “validation” step crosses a trust boundary and becomes an execution sink.
The streaming path can also reach this sink when the request is classified into the component-generation branch:
3. Proof of Concept (PoC)
- Send a request to the Agentic Assistant endpoint.
- Provide input that causes the model to return malicious component code.
- The returned code reaches the validation path.
- During validation, the server dynamically executes the generated Python.
- Arbitrary server-side code execution occurs.
4. Impact
-
Attackers who can access the Agentic Assistant feature and influence model output may execute arbitrary Python code on the server.
-
This can lead to:
- OS command execution
- file read/write
- credential or secret disclosure
- full compromise of the Langflow process
5. Exploitability Notes
This issue is most accurately described as an authenticated or feature-reachable code execution vulnerability, rather than an unconditional unauthenticated remote attack.
Severity depends on deployment model:
- In local-only, single-user development setups, the issue may be limited to self-exposure by the operator.
- In shared, team, or internet-exposed deployments, it may be exploitable by other users or attackers who can reach the assistant feature.
The assistant feature depends on an active user context:
Authentication sources include bearer token, cookie, or API key:
Default deployment settings may widen exposure, including AUTO_LOGIN=true and the /api/v1/auto_login endpoint:
6. Patch Recommendation
- Remove all dynamic execution from the validation path.
- Ensure validation is strictly static and side-effect-free.
- Treat all LLM output as untrusted input.
- If code generation must be supported, require explicit approval and run it in a hardened sandbox isolated from the main server process.
Discovered by: @kexinoh (https://github.com/kexinoh, works at Tencent Zhuque Lab)
Affected versions
PyPI
| Package | Vulnerable | Fixed in |
|---|---|---|
| langflow | < 1.9.0 |
1.9.0 |
How to fix
Move to the fixed version or later with your package manager, update the lockfile, and run your tests. If the package only arrives through another dependency, upgrade that dependency first. If none of its releases pulls a fixed version yet, force the version with your package manager's override.
langflow PyPI → 1.9.0
- pip
pip install --upgrade "langflow>=1.9.0"- poetry
poetry add "langflow>=1.9.0"- uv
uv add "langflow>=1.9.0"
Severity breakdown
CVSS 4.0 0.0
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:H/SI:H/SA:N
- Attack vector
- Network
- Attack complexity
- Low
- Attack requirements
- None
- Privileges required
- Low
- User interaction
- None
- Confidentiality (vulnerable system)
- High
- Integrity (vulnerable system)
- High
- Availability (vulnerable system)
- None
- Confidentiality (subsequent systems)
- High
- Integrity (subsequent systems)
- High
- Availability (subsequent systems)
- None
CVSS 3.1 9.9
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
- Attack vector
- Network
- Attack complexity
- Low
- Privileges required
- Low
- User interaction
- None
- Scope
- Changed
- Confidentiality
- High
- Integrity
- High
- Availability
- High
Weakness
CWE-94: Improper Control of Generation of Code ('Code Injection')
The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.
How to prevent it
- Architecture and Design: Refactor your program so that you do not have to dynamically generate code.
- Architecture and Design: Run your code in a "jail" or similar sandbox environment that enforces strict boundaries between the process and the operating system. This may effectively restrict which code can be executed by your product. Examples include the Unix chroot jail and AppArmor. In general, managed code may provide some protection. This may not be a feasible solution, and it only limits the impact to the operating system; the rest of your application may still be subject to compromise. Be careful to avoid CWE-243 and other weaknesses related to jails.
- Implementation: Assume all input is malicious. Use an "accept known good" input validation strategy, i.e., use a list of acceptable inputs that strictly conform to specifications. Reject any input that does not strictly conform to specifications, or transform it into something that does. When performing input validation, consider all potentially relevant properties, including length, type of input, the full range of acceptable values, missing or extra inputs, syntax, consistency across related fields, and conformance to business rules. As an example of business rule logic, "boat" may be syntactically valid because it only contains alphanumeric characters, but it is not valid if the input is only expected to contain colors such as "red" or "blue." Do not rely exclusively on looking for malicious or malformed inputs. This is likely to miss at least one undesirable input, especially if the code's environment changes. This can give attackers enough room to bypass the intended validation. However, denylists can be useful for detecting potential attacks or determining which inputs are so malformed that they should be rejected outright. To reduce the likelihood of code injection, use stringent allowlists that limit which constructs are allowed. If you are dynamically constructing code that invokes a function, then verifying that the input is alphanumeric might be insufficient. An attacker might still be able to reference a dangerous function that you did not intend to allow, such as system(), exec(), or exit().
- Testing: Use dynamic tools and techniques that interact with the product using large test suites with many diverse inputs, such as fuzz testing (fuzzing), robustness testing, and fault injection. The product's operation may slow down, but it should not become unstable, crash, or generate incorrect results.
- Operation: Run the code in an environment that performs automatic taint propagation and prevents any command execution that uses tainted variables, such as Perl's "-T" switch. This will force the program to perform validation steps that remove the taint, although you must be careful to correctly validate your inputs so that you do not accidentally mark dangerous inputs as untainted (see CWE-183 and CWE-184).
- Operation: Run the code in an environment that performs automatic taint propagation and prevents any command execution that uses tainted variables, such as Perl's "-T" switch. This will force the program to perform validation steps that remove the taint, although you must be careful to correctly validate your inputs so that you do not accidentally mark dangerous inputs as untainted (see CWE-183 and CWE-184).
- Implementation: For Python programs, it is frequently encouraged to use the ast.literal_eval() function instead of eval, since it is intentionally designed to avoid executing code. However, an adversary could still cause excessive memory or stack consumption via deeply nested structures [REF-1372], so the python documentation discourages use of ast.literal_eval() on untrusted data [REF-1373].
References
Advisories
Packages
Other links
- github.com/langflow-ai/langflow/security/advisories/GHSA-v8hw-mh8c-jxfc
- github.com/pypa/advisory-database/tree/main/vulns/langflow/PYSEC-2026-82.yaml
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
- github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/s…
Timeline
- Published
- Last updated by the source
- Latest EPSS score
Related advisories
| Advisory | Severity | Why it's related |
|---|---|---|
| GHSA-qrpv-q767-xqq2 Langflow: IDOR Vulnerability in `/api/v1/responses` Endpoint Allows Authenticated Attackers to Access Another User's Flow | High Known exploited | Also affects langflow |
| GHSA-vwmf-pq79-vjvx Unauthenticated Remote Code Execution in Langflow via Public Flow Build Endpoint | Critical Known exploited | Also affects langflow |
| GHSA-g22f-v6f7-2hrh Langflow affected by Remote Code Execution via validate_code() exec() | High Known exploited | Also affects langflow |
| GHSA-577h-p2hh-v4mv Langflow CORS misconfiguration enables Account Takeover and RCE | Critical Known exploited | Also affects langflow |
| GHSA-rvqx-wpfh-mfx7 Langflow Unauth RCE | Critical Known exploited | Also affects langflow |
| GHSA-j8f7-x8jm-wmm4 Langflow: SSRF in URL-taking components (protection disabled by default / warn-only, not applied to RSS, SearXNG, Web Search, Home Assistant, Glean, Docling) | Medium | Also affects langflow |
| GHSA-4f6c-2vvp-gw82 Langflow: IP Spoofing Bypass via `X-Forwarded-For` Allowing Remote Configuration Write | High | Also affects langflow |
| GHSA-4hmc-cfm3-w43c Langflow has Authenticated Cross-Project File Disclosure via Unscoped MCP Resource Handlers | High | Also affects langflow |
MergeHarbor checks every repository's dependencies against this database, ranks what matters by exploitability and reachability, routes it to the owning team and opens the fix pull request.
Check your repos with MergeHarbor