CVE-2025-55284
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. Prior to version 1.0.4, it's possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation due to an overly broad allowlist of safe commands. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update received this fix automatically after release. Current users of Claude Code are unaffected, as versions prior to 1.0.24 are deprecated and have been forced to update.
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 confidenceClaude Code prior to 1.0.4 contained an overly broad allowlist of safe commands that could be bypassed to read files and exfiltrate their contents over the network without triggering user confirmation prompts. Exploitation requires an attacker to inject untrusted content into the Claude Code context window.
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< 1.0.4CVSS 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
- None
- Availability
- None
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
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.
-
Verify Claude Code is installedRun 'claude --version' or 'claude -v' in your terminal. If the command is not found, Claude Code is not installed.Affected if Claude Code is installed and the version is less than 1.0.4
-
Determine installed Claude Code versionExecute the version check command (claude --version) and note the version number displayed.Affected if The displayed version is any release prior to 1.0.4 (for example, 1.0.3, 1.0.2, 1.0.1, etc.)
-
Confirm the vulnerability requires user context interactionThis vulnerability is triggered only when an attacker can inject untrusted content into your Claude Code context window. Assess whether you interact with Claude Code in environments where external or untrusted content could be introduced (for example, pasting code from unknown sources, processing untrusted files, or using Claude Code with third-party integrations).Affected if You use Claude Code with external or untrusted inputs and your version is below 1.0.4
You are affected if Claude Code is installed with a version lower than 1.0.4 and you use it in contexts where untrusted content could be injected into the context window.
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 · scoped1.0.4
Ensure Claude Code is updated to version 1.0.4 or later; the vendor reports auto-update and forced updates have already patched most installations.
Claude Code 1.0.4 or later (current stable releases are 1.0.24+)
- Check current Claude Code version by opening Claude Code and navigating to Settings > About, or running `claude --version` in the terminal
- If version is below 1.0.4, ensure auto-update is enabled in Claude Code settings
- Manually update to version 1.0.4 or later by downloading the latest release from the official Claude Code distribution channels
- Restart Claude Code after updating to ensure the fix is fully applied
- Verify the updated version by checking Settings > About again
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-2025-55284 — 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-2025-55284 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