# CVE-2026-18830: Insufficient input validation in Amazon Bedrock AgentCore harness InvokeHarness API

> Authenticated users can bypass security controls and execute tools via crafted messages in Amazon Bedrock AgentCore harness.

- **Severity:** High 8.6 (`CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N`)
- **Exploited in the wild:** Not known
- **Login needed:** Any signed-in user
- **Attackable:** Over the internet
- **Victim action needed:** Not needed
- **Fix available:** No
- **Published:** 4 Aug 2026
- **Updated:** 11 Oct 2026
- **Also known as:** GHSA-h8gv-mm2p-4q56

## What is CVE-2026-18830?

CVE-2026-18830 is a high-severity vulnerability in AWS Amazon Bedrock AgentCore harness, published on 4 Aug 2026. Any signed-in user can exploit it over the network, with no action from the victim.

### Official description

Insufficient input validation in Amazon Bedrock AgentCore harness might allow an authenticated remote user to execute configured tools bypassing model invocation and security controls via crafted content blocks in conversation messages. AWS has addressed this issue. No customer action is required.

Weakness: CWE-1287 (Improper Validation of Specified Type of Input)

## Which versions are affected by CVE-2026-18830?


## How do I fix CVE-2026-18830?

No fix has been published for CVE-2026-18830 yet. Limit exposure of the affected software until one is available.

## Is CVE-2026-18830 being exploited?

There is no known exploitation of CVE-2026-18830 in the wild and no public exploit code.

Public exploit code:

- AegisAgent - Runtime security gateway & privilege governance for AI agents. Cryptographic tool-call provenance (CoreBreak/CVE-2026-18830/18236/64650 defense), policy engine, sandbox isolation, HITL approval, MCP security proxy, tamper-evident audit. (github_poc): https://github.com/huzjie/aegisagent

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2026-18830 and fix it if it is affected.

What it is: CVE-2026-18830 is a high-severity vulnerability in AWS Amazon Bedrock AgentCore harness, published on 4 Aug 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Exploitation: There is no known exploitation of CVE-2026-18830 in the wild and no public exploit code.

Affected product: AWS Amazon Bedrock AgentCore harness. No package-level version data is available, so check the vendor advisory linked from the reference page.

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2026-18830/ (Markdown: https://insights.sbomify.com/CVE-2026-18830/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2026-18830
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-18830
- OSV: https://osv.dev/vulnerability/CVE-2026-18830

---
From sbomify Insights: https://insights.sbomify.com/CVE-2026-18830/
Summaries are generated and may contain mistakes; the official description above is the record.