Skip to content

EEF-CVE-2026-88257 CVE-2026-88257 GHSA-mrg2-4747-fmpw

beam_mcp: nested tool argument constraints advertised but not enforced

Not rated yet Hex
Severity
0.0 / 10
Unknown · CVSS 4.0
Exploit chance (EPSS)
0.27%
Chance of exploitation in the next 30 days. Higher than 19.00% of scored vulnerabilities.
Known exploited
No
Not in CISA's catalog
Weakness
CWE-20 Improper Input Validation
Fix
0.10.1
Upgrade beam_mcp to this version or later

Description

Summary

Improper Input Validation vulnerability in BeamMCP.Schema in ScriptKittyOS beam_mcp allows an MCP client to reach a tool's dispatch function with arguments that violate the input schema the server advertised. BeamMCP.Schema.validate/2 checked type, required, additionalProperties, enum and numeric bounds on the top-level arguments object only. Constraints inside nested objects and on array items (items, minItems, maxItems, minLength, maxLength, pattern, nested required, enum and additionalProperties: false) were advertised by tools/list and never checked at tools/call or prompts/get, and keywords outside the enforced subset (oneOf, anyOf, $ref) were advertised and ignored.

A host whose dispatch code relies on the schema it declared receives values the schema forbids, such as an out-of-range number or an undeclared key inside a nested object. What the host does with such a value decides the impact.

This issue affects beam_mcp: from 0.1.0 before 0.10.1.

Details

1. Advertising. tools/list returns each tool's input_schema verbatim, including nested properties, items and constraint keywords.

2. Validation. BeamMCP.Schema.validate/2 in lib/beam_mcp/schema.ex walks only the first level: check_required/2 and check_additional/3 run on the top-level object, and check_properties/2 applies check_type, check_enum and check_range to each top-level value. A value of type object or array is accepted once its own type matches, and its contents are not visited. Keywords the validator does not know are ignored.

3. Dispatch. BeamMCP.Server.validate_and_dispatch/3 passes the accepted arguments to normalize_arguments/2 and then to the host's dispatch function, so an undeclared key inside a nested object, an out-of-range nested number, or an array item of the wrong type reaches host code that believed the schema excluded it. The same validator runs on prompts/get arguments. The fix in 0.10.1 enforces every keyword of the documented subset at every depth and refuses a schema that uses any other keyword when the catalog is loaded.

Proof of concept

  1. Declare a tool whose input_schema has a nested object property opts with "properties": {"level": {"type": "integer", "maximum": 3}}, "required": ["level"] and "additionalProperties": false, and an array property tags with "items": {"type": "string"} and "maxItems": 2.
  2. Send tools/call with "arguments": {"opts": {"level": 99, "extra": "x"}}.
  3. On beam_mcp 0.10.0 the dispatch function receives %{opts: %{"extra" => "x", "level" => 99}}. On 0.10.1 the call is refused with invalid arguments: unknown property: opts.extra.
  4. Send "arguments": {"tags": [1, 2, 3]}. On 0.10.0 the dispatch function receives tags: [1, 2, 3]. On 0.10.1 the call is refused with tags must have at most 2 items.

Impact

An MCP client can hand a host's tool values the host's declared schema forbids, such as an out-of-range number or an undeclared key inside a nested object. The consequence depends on what the host's dispatch code does with a value it never expected to receive.

Workarounds

Re-validate the arguments inside the host's dispatch function against every constraint the schema declares below the top level, or move each constraint to a top-level property, which the affected versions do enforce.

Affected versions

Hex

PackageVulnerableFixed in
beam_mcp
>= 0.1.0, < 0.10.1
0.10.1

How to fix

Move to the fixed version or later with your package manager, update the lockfile, and run your tests. If the package only arrives through another dependency, upgrade that dependency first. If none of its releases pulls a fixed version yet, force the version with your package manager's override.

beam_mcp Hex → 0.10.1

mix
{:beam_mcp, "~> 0.10.1"} # then: mix deps.update beam_mcp

Severity breakdown

CVSS 4.0 0.0

CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N

Attack vector
Network
Attack complexity
Low
Attack requirements
None
Privileges required
Low
User interaction
None
Confidentiality (vulnerable system)
None
Integrity (vulnerable system)
Low
Availability (vulnerable system)
None
Confidentiality (subsequent systems)
None
Integrity (subsequent systems)
None
Availability (subsequent systems)
None

Weakness

CWE-20: Improper Input Validation

The product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly.

How to prevent it
  • Architecture and Design: Consider using language-theoretic security (LangSec) techniques that characterize inputs using a formal language and build "recognizers" for that language. This effectively requires parsing to be a distinct layer that effectively enforces a boundary between raw input and internal data representations, instead of allowing parser code to be scattered throughout the program, where it could be subject to errors or inconsistencies that create weaknesses. [REF-1109] [REF-1110] [REF-1111]
  • Architecture and Design: Use an input validation framework such as Struts or the OWASP ESAPI Validation API. Note that using a framework does not automatically address all input validation problems; be mindful of weaknesses that could arise from misusing the framework itself (CWE-1173).
  • Architecture and Design, Implementation: Understand all the potential areas where untrusted inputs can enter the product, including but not limited to: parameters or arguments, cookies, anything read from the network, environment variables, reverse DNS lookups, query results, request headers, URL components, e-mail, files, filenames, databases, and any external systems that provide data to the application. Remember that such inputs may be obtained indirectly through API calls.
  • Implementation: Assume all input is malicious. Use an "accept known good" input validation strategy, i.e., use a list of acceptable inputs that strictly conform to specifications. Reject any input that does not strictly conform to specifications, or transform it into something that does. When performing input validation, consider all potentially relevant properties, including length, type of input, the full range of acceptable values, missing or extra inputs, syntax, consistency across related fields, and conformance to business rules. As an example of business rule logic, "boat" may be syntactically valid because it only contains alphanumeric characters, but it is not valid if the input is only expected to contain colors such as "red" or "blue." Do not rely exclusively on looking for malicious or malformed inputs. This is likely to miss at least one undesirable input, especially if the code's environment changes. This can give attackers enough room to bypass the intended validation. However, denylists can be useful for detecting potential attacks or determining which inputs are so malformed that they should be rejected outright.
  • Architecture and Design: For any security checks that are performed on the client side, ensure that these checks are duplicated on the server side, in order to avoid CWE-602. Attackers can bypass the client-side checks by modifying values after the checks have been performed, or by changing the client to remove the client-side checks entirely. Then, these modified values would be submitted to the server. Even though client-side checks provide minimal benefits with respect to server-side security, they are still useful. First, they can support intrusion detection. If the server receives input that should have been rejected by the client, then it may be an indication of an attack. Second, client-side error-checking can provide helpful feedback to the user about the expectations for valid input. Third, there may be a reduction in server-side processing time for accidental input errors, although this is typically a small savings.
  • Implementation: When your application combines data from multiple sources, perform the validation after the sources have been combined. The individual data elements may pass the validation step but violate the intended restrictions after they have been combined.
  • Implementation: Be especially careful to validate all input when invoking code that crosses language boundaries, such as from an interpreted language to native code. This could create an unexpected interaction between the language boundaries. Ensure that you are not violating any of the expectations of the language with which you are interfacing. For example, even though Java may not be susceptible to buffer overflows, providing a large argument in a call to native code might trigger an overflow.
  • Implementation: Directly convert your input type into the expected data type, such as using a conversion function that translates a string into a number. After converting to the expected data type, ensure that the input's values fall within the expected range of allowable values and that multi-field consistencies are maintained.
  • Implementation: Inputs should be decoded and canonicalized to the application's current internal representation before being validated (CWE-180, CWE-181). Make sure that your application does not inadvertently decode the same input twice (CWE-174). Such errors could be used to bypass allowlist schemes by introducing dangerous inputs after they have been checked. Use libraries such as the OWASP ESAPI Canonicalization control. Consider performing repeated canonicalization until your input does not change any more. This will avoid double-decoding and similar scenarios, but it might inadvertently modify inputs that are allowed to contain properly-encoded dangerous content.
  • Implementation: When exchanging data between components, ensure that both components are using the same character encoding. Ensure that the proper encoding is applied at each interface. Explicitly set the encoding you are using whenever the protocol allows you to do so.

References

Timeline

  1. Published
  2. Last updated by the source
  3. Latest EPSS score
AdvisorySeverityWhy it's related
EEF-CVE-2026-104634
beam_mcp: JSON boolean and null tool arguments reach dispatch as strings
Not rated yet Also affects beam_mcp
GHSA-m665-v7pm-7grj
zip: Critical Parser Differential & Security Control Bypass via Dual-Header Inconsistencies (Zip Cloaking) Leading to Arbitrary File Overwrite & RCE
Critical Same weakness, CWE-20
GHSA-g5ff-637f-6q2m
LiteLLM: internal_user_viewer arbitrary local file read via `vertex_ai_credentials`
High Same weakness, CWE-20
GHSA-h3rc-j82p-2c3h
vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
High Same weakness, CWE-20
GHSA-8c8m-p3m8-cjg8
Nodemailer: A nested comment ends early in addressparser, releasing the rest of the comment as a recipient
Medium Same weakness, CWE-20
GHSA-m943-m63m-w62w
Nodemailer: A ";" inside a quoted string or comment ends an address group early in addressparser, turning display text into a recipient
Medium Same weakness, CWE-20
GHSA-85x2-q946-cp5h
Nodemailer: A ">" inside a quoted local part ends an angle-addr early in addressparser, delivering to a domain the header does not name
Medium Same weakness, CWE-20
GHSA-5hx5-vpf9-5wcv
pypdf: Unvalidated JPEG image data loading
Low Same weakness, CWE-20

Credits: Ayla Croft / Script Kitty OS, Jonatan Männchen / EEF

Is this in your code?

MergeHarbor checks every repository's dependencies against this database, ranks what matters by exploitability and reachability, routes it to the owning team and opens the fix pull request.

Check your repos with MergeHarbor