Staging Environment: Content and features may be unstable or change without notice.
Advisory details: pypa / langflow/PYSEC-2026-82
Advisory ID pypa/langflow/PYSEC-2026-82
Aliases CVE-2026-33873
GHSA-v8hw-mh8c-jxfc
PYSEC-2026-82
Summary Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, 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. Version 1.9.0 fixes the issue.
Status Published
Exploitability 0.5
Weighted Severity 8.9
Risk 4.5
Affected and Fixed Packages Package Details
Introduced and Fixed Package Commit Patches Package Commit Patches Details
Weaknesses (0)
There are no known CWE.
Reference id Reference type URL
assistant_service.py#L142-L156 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/services/assistant_service.py#L142-L156
assistant_service.py#L259-L300 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/services/assistant_service.py#L259-L300
assistant_service.py#L58-L79 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/services/assistant_service.py#L58-L79
auth.py#L71-L87 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/lfx/src/lfx/services/settings/auth.py#L71-L87
code_extraction.py#L11-L53 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/helpers/code_extraction.py#L11-L53
core.py#L38 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/api/utils/core.py#L38
GHSA-v8hw-mh8c-jxfc Other https://github.com/langflow-ai/langflow/security/advisories/GHSA-v8hw-mh8c-jxfc
login.py#L96-L135 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/api/v1/login.py#L96-L135
router.py#L252-L297 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/api/router.py#L252-L297
schemas.py#L20-L31 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/api/schemas.py#L20-L31
utils.py#L156-L163 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/services/auth/utils.py#L156-L163
utils.py#L39-L53 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/services/auth/utils.py#L39-L53
validate.py#L241-L272 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/lfx/src/lfx/custom/validate.py#L241-L272
validate.py#L394-L399 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/lfx/src/lfx/custom/validate.py#L394-L399
validate.py#L441-L443 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/lfx/src/lfx/custom/validate.py#L441-L443
validation.py#L27-L47 Other https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/helpers/validation.py#L27-L47
No exploits are available.

No EPSS data available for this advisory.

Patch URL
There are no known patches.
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H Found at https://github.com/pypa/advisory-database/blob/main/vulns/langflow/PYSEC-2026-82.yaml
Attack Vector (AV) Attack Complexity (AC) Privileges Required (PR) User Interaction (UI) Scope (S) Confidentiality Impact (C) Integrity Impact (I) Availability Impact (A)

network

adjacent_network

local

physical

low

high

none

low

high

none

required

unchanged

changed

high

low

none

high

low

none

high

low

none

Vector: SSVCv2/E:N/A:N/T:T/P:M/B:A/M:M/D:T/2026-04-01T03:55:31Z/

Decision: Track

Source URL: https://github.com/cisagov/vulnrichment/blob/develop/2026/33xxx/CVE-2026-33873.json

Source Advisory: vulnrichment/CVE-2026-33873

View SSVC decision tree
[{'Exploitation': 'none'},
 {'Automatable': 'no'},
 {'Technical Impact': 'total'},
 {'Mission Prevalence': 'minimal'},
 {'Public Well-being Impact': 'material'},
 {'Mission & Well-being': 'medium'}]