CVE-2025-46059
Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.
NVD · uneditedlangchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit component. This vulnerability allows attackers to execute arbitrary code and compromise the application via a crafted email message. NOTE: this is disputed by the Supplier because the code-execution issue was introduced by user-written code that does not adhere to the LangChain security practices.
Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.
dbcve analysis · moderate confidenceThis is an indirect prompt injection vulnerability in LangChain's GmailToolkit (v0.3.51) where a maliciously crafted email message can inject arbitrary prompts into the LLM processing pipeline, potentially leading to code execution. The attacker sends specially crafted email content that gets processed by the toolkit and passed to an LLM without proper input sanitization or prompt isolation, allowing the injected content to influence LLM behavior. The supplier disputes this as a vulnerability, claiming the code execution results from user code not following LangChain security practices.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.
From the vector- Attack vector
- Network
- Complexity
- Low
- Privileges
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.
dbcve checksWork through these to decide whether this CVE applies to you.
-
Identify LangChain GmailToolkit usageSearch your codebase for imports of langchain.tools.gmail or GmailToolkit, and review any files that handle email content processingAffected if GmailToolkit is imported and used in the codebase
-
Check installed LangChain versionRun 'pip show langchain' or check your dependency lock file (requirements.txt, pyproject.toml) for the langchain version numberAffected if Version is 0.3.51 or falls within the vulnerable range around this version
-
Trace how email content (subject, body, sender) flows from GmailToolkit to your LLM chain; look for the chain or agent invocation that processes email dataAffected if Email content is passed directly to an LLM without intermediate processing
-
Inspect input handling on email dataSearch for any sanitization, validation, or prompt isolation logic applied to email content before LLM invocation (e.g., input validators, prompt templates with isolation)Affected if No sanitization or prompt isolation is applied to raw email content before LLM processing
-
Review prompt construction methodExamine how prompts are built when email data is included; look for whether email content is placed in user messages without isolation from system promptsAffected if Email content is injected into prompts without proper separation from system instructions
You are affected if your application uses LangChain GmailToolkit (around v0.3.51) and processes email content through an LLM without sanitizing or isolating the email input from the prompt structure.
Generated from the published advisory. Verify against your own configuration.
Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.
From vendor dataImplement input validation and sanitization for all email content before it reaches the LLM, use prompt isolation techniques such as separate system prompts or parameterization, and ensure any user-provided code adheres to LangChain's documented security practices for handling external inputs. Consider adding warning documentation about the risks of processing untrusted email content.
- Consultation4.0 h
- Implementation12.0 h
- Testing8.0 h
- Review / QA4.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $7,808.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2025-46059 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2025-46059 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
No notes yet
Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.
A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.
- Verified mitigations, workarounds, and config changes
- Version or environment caveats, and links to real fixes
- No weaponised exploit code, or anything meant to cause harm
- No spam, self-promotion, credentials, or personal data