Loading story…
pipeboard-co disclosed and fixed a critical vulnerability in meta-ads-mcp that allowed unauthenticated users to execute MCP tools over HTTP and potentially obtain the operator’s Meta access token. The issue, tracked as GHSA-9gw6-46qc-99vr, affected version 1.0.101 and earlier, particularly in self-hosted deployments using --transport streamable-http on a network-reachable port. The flaw stemmed from authentication middleware forwarding requests without enforcing authorization, allowing downstream handlers to run with the server’s META_ACCESS_TOKEN when no per-request credential was supplied.
The advisory said a second bug in api.py appended the token to Meta Graph API request URLs and returned the raw request_url in JSON-RPC error responses, creating a direct token leakage path. A proof of concept showed an unauthenticated POST to /mcp returning 200 OK and exposing the access_token after a Graph API error. Release 1.0.109 changes unauthenticated behavior to return 401 Unauthorized with a WWW-Authenticate: Bearer header, redacts access_token and appsecret_proof from Graph API error payloads, and adds SECURITY.md. Operators were urged to upgrade immediately, rotate Meta access tokens if vulnerable instances were exposed to untrusted networks, and review Graph API access logs for misuse.
See affected versions and whether adversaries are exploiting it.
3 events from the most recent confirmed update back to the earliest known activity.
The vulnerability previously tracked as GHSA-9gw6-46qc-99vr was published as CVE-2026-48039, covering unauthenticated HTTP MCP tool execution and leakage of the operator's Meta access token in meta-ads-mcp versions before 1.0.109. The CVE assigned a CVSS 3.1 score of 9.1 (Critical) and mapped the issue to CWE-287.
Release 1.0.109 fixed GHSA-9gw6-46qc-99vr by changing HTTP middleware so unauthenticated requests return 401 instead of reaching tool handlers. The release also redacted access_token and appsecret_proof from Graph API error payloads and added a SECURITY.md file.
A GitHub security advisory disclosed GHSA-9gw6-46qc-99vr affecting meta-ads-mcp version 1.0.101 and earlier. The advisory described unauthenticated HTTP MCP tool execution that could leak the operator’s Meta access token and enable attacker actions against connected ad accounts.
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
See whether adversaries are exploiting this yet, and where the affected versions run in your environment.
4 references tracked. Mallory keeps watching after this page renders.
cvefeed.io
Open sourcegithub.com
Open sourcegithub.com
Open sourcegithub.com
Open sourceMap indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
A high-severity OAuth credential-disclosure vulnerability in Anthropic's official Model Context Protocol (MCP) Python SDK can allow a malicious HTTP MCP server to capture OAuth client secrets, authorization codes, PKCE verifiers, and ultimately valid access tokens. The attack abuses authorization-server discovery: an attacker-controlled server returns a `404` for modern discovery to trigger a legacy fallback that does not validate the issuer, then supplies malicious authorization metadata or token endpoints while presenting a legitimate identity-provider login flow to the user. The issue affects `mcp` versions 1.9.1 through 1.29.1 and 2.0.0 through 2.1.1, including `OAuthClientProvider`, `ClientCredentialsOAuthProvider`, and `PrivateKeyJWTOAuthProvider` configurations using vulnerable OAuth providers. It is fixed in versions 1.30.0 and 2.2.0; organizations should upgrade, explicitly bind machine-to-machine or pre-provisioned credentials to the expected issuer, remove legacy stored registrations, and rotate exposed client secrets and revoke potentially compromised tokens. No CVE or confirmed exploitation had been reported.
Sep 30, 2026
Researchers disclosed multiple security flaws affecting AWS MCP components, including a local file inclusion bug in the AWS Remote MCP Server and a critical command injection issue in `aws-mcp-server`. Varonis said authenticated users could abuse AWS CLI shorthand syntax, specifically the `@=` operator passed through the `aws___call_aws` tool, to read arbitrary files from the underlying host even when `FileAccessMode=NO_ACCESS` was enabled. AWS assigned **CVE-2026-4270** to the file access restriction bypass and said the issue was fixed in `aws-api-mcp-server` version **1.3.9**; the exposure affected the public endpoint `aws-mcp.us-east-1.api.aws` as well as self-hosted or forked deployments. A separate flaw, tracked as **CVE-2026-5058** and published by Trend Micro's Zero Day Initiative as **ZDI-26-246**, allows unauthenticated remote code execution in `aws-mcp-server` because user-supplied input in the allowed-commands list is not properly validated before being used in a system call. ZDI rated the bug **CVSS 9.8** and said successful exploitation lets attackers run arbitrary code in the MCP server context; the advisory was released as a 0-day after the vendor rejected the report. The disclosures landed alongside another AWS bulletin for **CVE-2026-4269**, an improper S3 ownership verification issue in the Bedrock AgentCore Starter Toolkit, underscoring broader security concerns around MCP-related tooling and the need for immediate patching and review of derivative implementations.
Jun 29, 2026
Chainlit released version **2.12.0** to remediate two unauthenticated vulnerabilities in its Model Context Protocol `/mcp` endpoint: critical command injection/RCE, **CVE-2026-45018** (CVSS 9.8), and high-severity SSRF, **CVE-2026-45019** (CVSS 7.2). Versions `2.4.0rc0` through `2.11.x` are affected when `features.mcp.enabled = true`. The command-injection issue allowed attackers to submit client-controlled stdio `fullCommand` values; configurations with no `allowed_executables` restriction could allow arbitrary commands through permitted tooling such as `npx -c`, executing under the Chainlit process account. The SSRF issue let attackers supply arbitrary HTTP/SSE MCP URLs and headers, enabling requests to loopback and private-network services, Docker sockets, Kubernetes APIs, databases, and cloud metadata endpoints such as `169.254.169.254`, with possible exposure of temporary cloud credentials. Version 2.12.0 requires server-side named configuration for stdio MCP servers and adds explicit opt-in allowlisting, destination revalidation, sensitive-header filtering, and redirect blocking for user-provided HTTP/SSE connections. Organizations should upgrade promptly; where that is not immediately possible, disable MCP with `features.mcp.enabled = false`, enforce authentication, and block server egress to internal networks and cloud-metadata services.
Aug 26, 2026