CVE-2025-54795
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 · uneditedClaude Code is an agentic coding tool. In versions below 1.0.20, an error in command parsing makes it possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. This is fixed in version 1.0.20.
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 · high confidenceA command parsing error in Claude Code versions below 1.0.20 allows attackers to bypass the built-in confirmation prompt and execute untrusted commands. Exploitation requires the ability to inject untrusted content into the Claude Code context window, making this a context-deserialization vulnerability in the command validation logic.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.
NVD · CPE data< 1.0.20CVSS 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.
-
Check Claude Code versionRun `claude --version` or `claude -v` in your terminal to determine the installed versionAffected if The version number displayed is less than 1.0.20 (for example, 1.0.19, 1.0.18, etc.)
-
Identify context window usageReview how Claude Code is being used - determine if it processes external content, files, or user inputs that could contain untrusted data in its context windowAffected if Claude Code is processing content from untrusted or external sources in its context window
-
Review input sourcesAudit the data sources feeding into Claude Code's context, including files, user prompts, API inputs, or integrations that could be controlled by external partiesAffected if Untrusted or user-controlled content can be injected into the context window without sanitization
-
Check for command execution patternsReview logs or session history if available to see if commands are being executed with and without confirmation promptsAffected if Commands execute without the expected confirmation prompt appearing
-
Verify patch availabilityCompare your current version against the fixed version 1.0.20 - any version below this is vulnerable to the parsing bypassAffected if Your installed version is below 1.0.20 and you process untrusted content in the context window
You are affected if Claude Code version is below 1.0.20 AND the context window feature processes potentially untrusted or injectable content.
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.
dbcve · scoped1.0.20
Upgrade Claude Code to version 1.0.20 or later to remediate this vulnerability.
Claude Code 1.0.20
- Check current Claude Code version using `claude --version` or equivalent command
- Download and install Claude Code version 1.0.20 from the official Anthropic source (docs.anthropic.com or github.com/anthropics/claude-code)
- Verify the upgrade was successful by checking the version again
- Ensure the new version is 1.0.20 or higher
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation1.0 h
- Implementation1.0 h
- Testing2.0 h
- Review / QA1.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $1,376.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2025-54795 — 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-2025-54795 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