How severe is GHSA-5474-4w2j-mq4c?

GHSA-5474-4w2j-mq4c has a CVSS score of 5.4/10, rated MEDIUM. Review your exposure and patch according to your risk tolerance.

Which packages are affected by GHSA-5474-4w2j-mq4c?

GHSA-5474-4w2j-mq4c affects the following packages: @anthropic-ai/sdk (npm). Ecosystems affected: npm.

How do I fix GHSA-5474-4w2j-mq4c?

Update @anthropic-ai/sdk to 0.81.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-5474-4w2j-mq4c is resolved across your whole dependency graph.

How do I detect GHSA-5474-4w2j-mq4c in my npm dependencies?

Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for @anthropic-ai/sdk. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.

How do I mitigate GHSA-5474-4w2j-mq4c if there is no patch (or I can't update yet)?

If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

How does O3 Security protect against GHSA-5474-4w2j-mq4c?

O3 pinpoints whether GHSA-5474-4w2j-mq4c is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Is GHSA-5474-4w2j-mq4c actively exploited in the wild?

No public exploit code has been indexed for GHSA-5474-4w2j-mq4c yet. This does not mean the vulnerability cannot be exploited — absence of public exploits does not imply safety. Apply the recommended fix and use O3 Security to monitor your exposure.

What is the EPSS score for GHSA-5474-4w2j-mq4c?

GHSA-5474-4w2j-mq4c has an EPSS (Exploit Prediction Scoring System) score of 0.3%, placing it in the 21th percentile of all CVEs. EPSS is maintained by FIRST.org and estimates the probability that a vulnerability will be exploited in the wild within the next 30 days. This score indicates relatively lower exploitation probability, though the CVSS severity should still guide your patching priority.

When was GHSA-5474-4w2j-mq4c published, and has it been updated?

GHSA-5474-4w2j-mq4c was published on April 1, 2026 and was last updated on May 5, 2026. Advisory data evolves as severity scores, affected ranges, and exploit intelligence are revised — always check the latest version of the advisory before acting.

GHSA-5474-4w2j-mq4c: @anthropic-ai/sdk (Medium 5.4)

EPSS Exploitation Probability

via FIRST.org ↗

0.3%probability of exploitation in next 30 days

Lower Risk21th percentile+0.27%

EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.

Blast Radius

1 pkg affected

📦@anthropic-ai/sdk

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects npm packages — download data is not available via public APIs for these ecosystems.

Description

The local filesystem memory tool in the Anthropic TypeScript SDK validated model-supplied paths using a string prefix check that did not append a trailing path separator. A model steered by prompt injection could supply a crafted path that resolved to a sibling directory sharing the memory root's name as a prefix, allowing reads and writes outside the sandboxed memory directory.

Users on the affected versions are advised to update to the latest version.

Claude SDK for TypeScript thanks hackerone.com/nicksim for reporting this issue!

Affected Packages

1 total 1 fixed

Ecosystem	Package	Vulnerable range	Fix
📦npm	`@anthropic-ai/sdk`	≥ 0.79.0&&< 0.81.0	0.81.0

Detection & mitigation playbook

Open-source dependency

Detect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for @anthropic-ai/sdk. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.
Fix
Update @anthropic-ai/sdk to 0.81.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-5474-4w2j-mq4c is resolved across your whole dependency graph.
Workarounds
If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.
How O3 protects you
O3 pinpoints whether GHSA-5474-4w2j-mq4c is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Tailored to GHSA-5474-4w2j-mq4c. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

The local filesystem memory tool in the Anthropic TypeScript SDK validated model-supplied paths using a string prefix check that did not append a trailing path separator. A model steered by prompt injection could supply a crafted path that resolved to a sibling directory sharing the memory root's name as a prefix, allowing reads and writes outside the sandboxed memory directory. Users on the affected versions are advised to update to the latest version. Claude SDK for TypeScript thanks [hackerone.com/nicksim](https://hackerone.com/nicksim) for reporting this issue!

O3 Security · Impact-Aware SCA

Is GHSA-5474-4w2j-mq4c in your dependencies?

O3 detects GHSA-5474-4w2j-mq4c across npm dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.

Scan my dependencies How O3 SCA works

GHSA-5474-4w2j-mq4c