During session resumption in crypto/tls, if the underlying Config has its ClientCAs or RootCAs fields mutated between the initial handshake and the resumed handshake, the resumed handshake may succeed when it should have failed. This may happen when a user calls Config.Clone and mutates the returned Config, or uses Config.GetConfigForClient. This can cause a client to resume a session with a server that it would not have resumed with during the initial handshake, or cause a server to resume a session with a client that it would not have resumed with during the initial handshake.

The net/http package improperly accepts a bare LF as a line terminator in chunked data chunk-size lines. This can permit request smuggling if a net/http server is used in conjunction with a server that incorrectly accepts a bare LF as part of a chunk-ext.

url.Parse insufficiently validated the host/authority component and accepted some invalid URLs.

Within HostnameError.Error(), when constructing an error string, there is no limit to the number of hosts that will be printed out. Furthermore, the error string is constructed by repeated string concatenation, leading to quadratic runtime. Therefore, a certificate provided by a malicious actor can result in excessive resource consumption.

The net/url package does not set a limit on the number of query parameters in a query.

While the maximum size of query parameters in URLs is generally limited by the maximum request header size, the net/http.Request.ParseForm method can parse large URL-encoded forms. Parsing a large form containing many unique query parameters can cause excessive memory consumption.

The ParseAddress function constructs domain-literal address components through repeated string concatenation. When parsing large domain-literal components, this can cause excessive CPU consumption.

The processing time for parsing some invalid inputs scales non-linearly with respect to the size of the input.

This affects programs which parse untrusted PEM inputs.

Validating certificate chains which contain DSA public keys can cause programs to panic, due to a interface cast that assumes they implement the Equal method.

This affects programs which validate arbitrary certificate chains.

Due to the design of the name constraint checking algorithm, the processing time of some inputs scale non-linearly with respect to the size of the certificate.

This affects programs which validate arbitrary certificate chains.

During session resumption in crypto/tls, if the underlying Config has its ClientCAs or RootCAs fields mutated between the initial handshake and the resumed handshake, the resumed handshake may succeed when it should have failed. This may happen when a user calls Config.Clone and mutates the returned Config, or uses Config.GetConfigForClient. This can cause a client to resume a session with a server that it would not have resumed with during the initial handshake, or cause a server to resume a session with a client that it would not have resumed with during the initial handshake.

The net/http package improperly accepts a bare LF as a line terminator in chunked data chunk-size lines. This can permit request smuggling if a net/http server is used in conjunction with a server that incorrectly accepts a bare LF as part of a chunk-ext.

url.Parse insufficiently validated the host/authority component and accepted some invalid URLs.

Within HostnameError.Error(), when constructing an error string, there is no limit to the number of hosts that will be printed out. Furthermore, the error string is constructed by repeated string concatenation, leading to quadratic runtime. Therefore, a certificate provided by a malicious actor can result in excessive resource consumption.

The net/url package does not set a limit on the number of query parameters in a query.

While the maximum size of query parameters in URLs is generally limited by the maximum request header size, the net/http.Request.ParseForm method can parse large URL-encoded forms. Parsing a large form containing many unique query parameters can cause excessive memory consumption.

The ParseAddress function constructs domain-literal address components through repeated string concatenation. When parsing large domain-literal components, this can cause excessive CPU consumption.

The processing time for parsing some invalid inputs scales non-linearly with respect to the size of the input.

This affects programs which parse untrusted PEM inputs.

Validating certificate chains which contain DSA public keys can cause programs to panic, due to a interface cast that assumes they implement the Equal method.

This affects programs which validate arbitrary certificate chains.

Due to the design of the name constraint checking algorithm, the processing time of some inputs scale non-linearly with respect to the size of the certificate.

This affects programs which validate arbitrary certificate chains.

Impact

What kind of vulnerability is it? Who is impacted?

It is an Authorization Bypass resulting from Improper Input Validation of the HTTP/2 :path pseudo-header.

The gRPC-Go server was too lenient in its routing logic, accepting requests where the :path omitted the mandatory leading slash (e.g., Service/Method instead of /Service/Method). While the server successfully routed these requests to the correct handler, authorization interceptors (including the official grpc/authz package) evaluated the raw, non-canonical path string. Consequently, "deny" rules defined using canonical paths (starting with /) failed to match the incoming request, allowing it to bypass the policy if a fallback "allow" rule was present.

Who is impacted?
This affects gRPC-Go servers that meet both of the following criteria:

1. They use path-based authorization interceptors, such as the official RBAC implementation in google.golang.org/grpc/authz or custom interceptors relying on info.FullMethod or grpc.Method(ctx).
2. Their security policy contains specific "deny" rules for canonical paths but allows other requests by default (a fallback "allow" rule).

The vulnerability is exploitable by an attacker who can send raw HTTP/2 frames with malformed :path headers directly to the gRPC server.

Patches

Has the problem been patched? What versions should users upgrade to?

Yes, the issue has been patched. The fix ensures that any request with a :path that does not start with a leading slash is immediately rejected with a codes.Unimplemented error, preventing it from reaching authorization interceptors or handlers with a non-canonical path string.

Users should upgrade to the following versions (or newer):

• v1.79.3
• The latest master branch.

It is recommended that all users employing path-based authorization (especially grpc/authz) upgrade as soon as the patch is available in a tagged release.

Workarounds

Is there a way for users to fix or remediate the vulnerability without upgrading?

While upgrading is the most secure and recommended path, users can mitigate the vulnerability using one of the following methods:

1. Use a Validating Interceptor (Recommended Mitigation)

Add an "outermost" interceptor to your server that validates the path before any other authorization logic runs:

func pathValidationInterceptor(ctx context.Context, req any, info *grpc.UnaryServerInfo, handler grpc.UnaryHandler) (any, error) {
    if info.FullMethod == "" || info.FullMethod[0] != '/' {
        return nil, status.Errorf(codes.Unimplemented, "malformed method name")
    }   
    return handler(ctx, req)
}

// Ensure this is the FIRST interceptor in your chain
s := grpc.NewServer(
    grpc.ChainUnaryInterceptor(pathValidationInterceptor, authzInterceptor),
)

2. Infrastructure-Level Normalization

If your gRPC server is behind a reverse proxy or load balancer (such as Envoy, NGINX, or an L7 Cloud Load Balancer), ensure it is configured to enforce strict HTTP/2 compliance for pseudo-headers and reject or normalize requests where the :path header does not start with a leading slash.

3. Policy Hardening

Switch to a "default deny" posture in your authorization policies (explicitly listing all allowed paths and denying everything else) to reduce the risk of bypasses via malformed inputs.

Impact

What kind of vulnerability is it? Who is impacted?

It is an Authorization Bypass resulting from Improper Input Validation of the HTTP/2 :path pseudo-header.

The gRPC-Go server was too lenient in its routing logic, accepting requests where the :path omitted the mandatory leading slash (e.g., Service/Method instead of /Service/Method). While the server successfully routed these requests to the correct handler, authorization interceptors (including the official grpc/authz package) evaluated the raw, non-canonical path string. Consequently, "deny" rules defined using canonical paths (starting with /) failed to match the incoming request, allowing it to bypass the policy if a fallback "allow" rule was present.

Who is impacted?
This affects gRPC-Go servers that meet both of the following criteria:

1. They use path-based authorization interceptors, such as the official RBAC implementation in google.golang.org/grpc/authz or custom interceptors relying on info.FullMethod or grpc.Method(ctx).
2. Their security policy contains specific "deny" rules for canonical paths but allows other requests by default (a fallback "allow" rule).

The vulnerability is exploitable by an attacker who can send raw HTTP/2 frames with malformed :path headers directly to the gRPC server.

Patches

Has the problem been patched? What versions should users upgrade to?

Yes, the issue has been patched. The fix ensures that any request with a :path that does not start with a leading slash is immediately rejected with a codes.Unimplemented error, preventing it from reaching authorization interceptors or handlers with a non-canonical path string.

Users should upgrade to the following versions (or newer):

• v1.79.3
• The latest master branch.

It is recommended that all users employing path-based authorization (especially grpc/authz) upgrade as soon as the patch is available in a tagged release.

Workarounds

Is there a way for users to fix or remediate the vulnerability without upgrading?

While upgrading is the most secure and recommended path, users can mitigate the vulnerability using one of the following methods:

1. Use a Validating Interceptor (Recommended Mitigation)

Add an "outermost" interceptor to your server that validates the path before any other authorization logic runs:

func pathValidationInterceptor(ctx context.Context, req any, info *grpc.UnaryServerInfo, handler grpc.UnaryHandler) (any, error) {
    if info.FullMethod == "" || info.FullMethod[0] != '/' {
        return nil, status.Errorf(codes.Unimplemented, "malformed method name")
    }   
    return handler(ctx, req)
}

// Ensure this is the FIRST interceptor in your chain
s := grpc.NewServer(
    grpc.ChainUnaryInterceptor(pathValidationInterceptor, authzInterceptor),
)

2. Infrastructure-Level Normalization

If your gRPC server is behind a reverse proxy or load balancer (such as Envoy, NGINX, or an L7 Cloud Load Balancer), ensure it is configured to enforce strict HTTP/2 compliance for pseudo-headers and reject or normalize requests where the :path header does not start with a leading slash.

3. Policy Hardening

Switch to a "default deny" posture in your authorization policies (explicitly listing all allowed paths and denying everything else) to reduce the risk of bypasses via malformed inputs.

Impact

What kind of vulnerability is it? Who is impacted?

It is an Authorization Bypass resulting from Improper Input Validation of the HTTP/2 :path pseudo-header.

The gRPC-Go server was too lenient in its routing logic, accepting requests where the :path omitted the mandatory leading slash (e.g., Service/Method instead of /Service/Method). While the server successfully routed these requests to the correct handler, authorization interceptors (including the official grpc/authz package) evaluated the raw, non-canonical path string. Consequently, "deny" rules defined using canonical paths (starting with /) failed to match the incoming request, allowing it to bypass the policy if a fallback "allow" rule was present.

Who is impacted?
This affects gRPC-Go servers that meet both of the following criteria:

1. They use path-based authorization interceptors, such as the official RBAC implementation in google.golang.org/grpc/authz or custom interceptors relying on info.FullMethod or grpc.Method(ctx).
2. Their security policy contains specific "deny" rules for canonical paths but allows other requests by default (a fallback "allow" rule).

The vulnerability is exploitable by an attacker who can send raw HTTP/2 frames with malformed :path headers directly to the gRPC server.

Patches

Has the problem been patched? What versions should users upgrade to?

Yes, the issue has been patched. The fix ensures that any request with a :path that does not start with a leading slash is immediately rejected with a codes.Unimplemented error, preventing it from reaching authorization interceptors or handlers with a non-canonical path string.

Users should upgrade to the following versions (or newer):

• v1.79.3
• The latest master branch.

It is recommended that all users employing path-based authorization (especially grpc/authz) upgrade as soon as the patch is available in a tagged release.

Workarounds

Is there a way for users to fix or remediate the vulnerability without upgrading?

While upgrading is the most secure and recommended path, users can mitigate the vulnerability using one of the following methods:

1. Use a Validating Interceptor (Recommended Mitigation)

Add an "outermost" interceptor to your server that validates the path before any other authorization logic runs:

func pathValidationInterceptor(ctx context.Context, req any, info *grpc.UnaryServerInfo, handler grpc.UnaryHandler) (any, error) {
    if info.FullMethod == "" || info.FullMethod[0] != '/' {
        return nil, status.Errorf(codes.Unimplemented, "malformed method name")
    }   
    return handler(ctx, req)
}

// Ensure this is the FIRST interceptor in your chain
s := grpc.NewServer(
    grpc.ChainUnaryInterceptor(pathValidationInterceptor, authzInterceptor),
)

2. Infrastructure-Level Normalization

If your gRPC server is behind a reverse proxy or load balancer (such as Envoy, NGINX, or an L7 Cloud Load Balancer), ensure it is configured to enforce strict HTTP/2 compliance for pseudo-headers and reject or normalize requests where the :path header does not start with a leading slash.

3. Policy Hardening

Switch to a "default deny" posture in your authorization policies (explicitly listing all allowed paths and denying everything else) to reduce the risk of bypasses via malformed inputs.

SSH clients receiving SSH_AGENT_SUCCESS when expecting a typed response will panic and cause early termination of the client process.

SSH servers which implement file transfer protocols are vulnerable to a denial of service attack from clients which complete the key exchange slowly, or not at all, causing pending content to be read into memory, but never transmitted.

OpenTelemetry-Go Contrib is a collection of third-party packages for OpenTelemetry-Go. Prior to version 0.46.0, the grpc Unary Server Interceptor out of the box adds labels net.peer.sock.addr and net.peer.sock.port that have unbound cardinality. It leads to the server's potential memory exhaustion when many malicious requests are sent. An attacker can easily flood the peer address and port for requests. Version 0.46.0 contains a fix for this issue. As a workaround to stop being affected, a view removing the attributes can be used. The other possibility is to disable grpc metrics instrumentation by passing otelgrpc.WithMeterProvider option with noop.NewMeterProvider.

Summary

Function parse.ParseUnverified currently splits (via a call to strings.Split) its argument (which is untrusted data) on periods.

As a result, in the face of a malicious request whose Authorization header consists of Bearer followed by many period characters, a call to that function incurs allocations to the tune of O(n) bytes (where n stands for the length of the function's argument), with a constant factor of about 16. Relevant weakness: CWE-405: Asymmetric Resource Consumption (Amplification)

Details

See parse.ParseUnverified

Impact

Excessive memory allocation

Impact

The OpenTelemetry Go SDK in version v1.20.0-1.39.0 is vulnerable to Path Hijacking (Untrusted Search Paths) on macOS/Darwin systems. The resource detection code in sdk/resource/host_id.go executes the ioreg system command using a search path. An attacker with the ability to locally modify the PATH environment variable can achieve Arbitrary Code Execution (ACE) within the context of the application.

Patches

This has been patched in d45961b, which was released with v1.40.0.

References

• CWE-426: Untrusted Search Path

Impact

The OpenTelemetry Go SDK in version v1.20.0-1.39.0 is vulnerable to Path Hijacking (Untrusted Search Paths) on macOS/Darwin systems. The resource detection code in sdk/resource/host_id.go executes the ioreg system command using a search path. An attacker with the ability to locally modify the PATH environment variable can achieve Arbitrary Code Execution (ACE) within the context of the application.

Patches

This has been patched in d45961b, which was released with v1.40.0.

References

• CWE-426: Untrusted Search Path

SSH clients receiving SSH_AGENT_SUCCESS when expecting a typed response will panic and cause early termination of the client process.

SSH clients receiving SSH_AGENT_SUCCESS when expecting a typed response will panic and cause early termination of the client process.

Impact

Decrypting a JSON Web Encryption (JWE) object will panic if the alg field indicates a key wrapping algorithm (one ending in KW, with the exception of A128GCMKW, A192GCMKW, and A256GCMKW) and the encrypted_key field is empty. The panic happens when cipher.KeyUnwrap() in key_wrap.go attempts to allocate a slice with a zero or negative length based on the length of the encrypted_key.

This code path is reachable from ParseEncrypted() / ParseEncryptedJSON() / ParseEncryptedCompact() followed by Decrypt() on the resulting object. Note that the parse functions take a list of accepted key algorithms. If the accepted key algorithms do not include any key wrapping algorithms, parsing will fail and the application will be unaffected.

This panic is also reachable by calling cipher.KeyUnwrap() directly with any ciphertext parameter less than 16 bytes long, but calling this function directly is less common.

Panics can lead to denial of service.

Fixed In

4.1.4 and v3.0.5

Workarounds

If the list of keyAlgorithms passed to ParseEncrypted() / ParseEncryptedJSON() / ParseEncryptedCompact() does not include key wrapping algorithms (those ending in KW), your application is unaffected.

If your application uses key wrapping, you can prevalidate to the JWE objects to ensure the encrypted_key field is nonempty. If your application accepts JWE Compact Serialization, apply that validation to the corresponding field of that serialization (the data between the first and second .).

Thanks

Thanks to Datadog's Security team for finding this issue.

An attacker can pass a malicious malformed token which causes unexpected memory to be consumed during parsing.

Summary

Function parse.ParseUnverified currently splits (via a call to strings.Split) its argument (which is untrusted data) on periods.

As a result, in the face of a malicious request whose Authorization header consists of Bearer followed by many period characters, a call to that function incurs allocations to the tune of O(n) bytes (where n stands for the length of the function's argument), with a constant factor of about 16. Relevant weakness: CWE-405: Asymmetric Resource Consumption (Amplification)

Details

See parse.ParseUnverified

Impact

Excessive memory allocation

An attacker can pass a malicious malformed token which causes unexpected memory to be consumed during parsing.