How severe is GHSA-xhcr-cqfr-m3hv?

No CVSS score has been assigned to GHSA-xhcr-cqfr-m3hv yet. Review the advisory details and affected package list to assess your exposure.

Which packages are affected by GHSA-xhcr-cqfr-m3hv?

GHSA-xhcr-cqfr-m3hv affects the following packages: atomic-agents-stack (PyPI). Ecosystems affected: PyPI.

How do I fix GHSA-xhcr-cqfr-m3hv?

Update atomic-agents-stack to 1.1.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-xhcr-cqfr-m3hv is resolved across your whole dependency graph.

How do I detect GHSA-xhcr-cqfr-m3hv in my PyPI dependencies?

Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for atomic-agents-stack, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

How do I mitigate GHSA-xhcr-cqfr-m3hv 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.

Is GHSA-xhcr-cqfr-m3hv actively exploited in the wild?

No public exploit code has been indexed for GHSA-xhcr-cqfr-m3hv 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-xhcr-cqfr-m3hv?

GHSA-xhcr-cqfr-m3hv has an EPSS (Exploit Prediction Scoring System) score of 0.3%, placing it in the 23th 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.

What type of vulnerability is GHSA-xhcr-cqfr-m3hv?

GHSA-xhcr-cqfr-m3hv is classified as CWE-319 (CWE-319). This weakness type describe the underlying flaw category, which helps determine the potential impact and the right class of mitigation.

When was GHSA-xhcr-cqfr-m3hv published, and has it been updated?

GHSA-xhcr-cqfr-m3hv was published on August 17, 2026 and was last updated on September 16, 2026. Advisory data evolves as severity scores, affected ranges, and exploit intelligence are revised — always check the latest version of the advisory before acting.

🐍 PyPI

Not in CISA KEV

GHSA-xhcr-cqfr-m3hv — atomic-agents-stack

GHSA-xhcr-cqfr-m3hv is a CWE-319 vulnerability in atomic-agents-stack. A fix is available for atomic-agents-stack — see the affected versions and patch details below.

atomic-agents-stack: HTTP MCP catalog accepts cleartext http and spawns catalog-supplied commands (MITM to RCE)

Also known asCVE-2026-91988

Published

Aug 17, 2026

Updated

Sep 16, 2026

Affected

1 pkg

Patched

1 / 1

Exploits

None indexed

Exploitation data as of Oct 2, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

No confirmed exploitation observed yet

A successful exploit gives an attacker total control of the affected component, not partial access.
CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.

Exploitation and automatability from CISA’s SSVC triage for GHSA-xhcr-cqfr-m3hv.

EPSS Exploitation Probability

via FIRST.org ↗

0.3%probability of exploitation in next 30 days

Lower Risk0.00%

Lower risk than most CVEs23th percentile — riskier than 23% of all scored CVEsHighest risk

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

Real-World Exposure

1 pkg affected

🐍atomic-agents-stack

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

Description

The HTTP MCP server-registry backend factory (atomic_agents/mcp_registry/http.py, make_http_mcp_server_registry_backend_from_url) accepts both http and https schemes. Catalog entries carry command/args that are type-validated but content-unrestricted, and are later spawned as local stdio subprocesses by MCPClientPool. Over a cleartext http:// catalog URL, a network man-in-the-middle can rewrite the catalog response to inject an arbitrary command/args and obtain code execution on the agent host, with no LLM involvement. The Policy MCP allowlist is not a default mitigation (mcp_allow_fn defaults to None), so absent an operator-authored allowlist every resolved spec connects.

Affected: mcp_registry/http.py, all versions through 1.0.0. (The https path is sound: httpx defaults to verify=True, follow_redirects=False.)

Fix: require https by default and gate http:// behind a loud explicit opt-in. Defense-in-depth: allowlist the resolved command basename (or require confirmation) before any registry-sourced subprocess spawn. Document the consequence in spec/36.

Affected Packages

1 total 1 fixed

Ecosystem	Package	Vulnerable range	Fix
🐍PyPI	`atomic-agents-stack`	all versions	1.1.0`pip install --upgrade 'atomic-agents-stack==1.1.0'`

Detection & mitigation playbook

Open-source dependency

Detect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for atomic-agents-stack, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
Fix
Update atomic-agents-stack to 1.1.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-xhcr-cqfr-m3hv 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.

Frequently Asked Questions

The HTTP MCP server-registry backend factory (`atomic_agents/mcp_registry/http.py`, `make_http_mcp_server_registry_backend_from_url`) accepts both `http` and `https` schemes. Catalog entries carry `command`/`args` that are type-validated but content-unrestricted, and are later spawned as local stdio subprocesses by `MCPClientPool`. Over a cleartext `http://` catalog URL, a network man-in-the-middle can rewrite the catalog response to inject an arbitrary `command`/`args` and obtain code execution on the agent host, with no LLM involvement. The Policy MCP allowlist is not a default mitigation (`

O3 Security · Impact-Aware SCA

Is GHSA-xhcr-cqfr-m3hv in your dependencies?

Find it across PyPI, including transitive dependencies.

Scan my dependencies How O3 SCA works