Critical Injection exploit reference

CVE-2026-27952 — Agenta has Python Sandbox Escape, Leading to Remote Code Execution (RCE)

Agenta is an open-source LLMOps platform. In Agenta-API prior to version 0.48.1, a Python sandbox escape vulnerability existed in Agenta's custom code evaluator. Agenta used RestrictedPython as a sandboxing mechanism for user-supplied evaluator code, but incorrectly whitelisted the `numpy` package as safe within the sandbox. This allowed authenticated users to bypass the sandbox and achieve arbitrary code execution on the API server. The escape path was through `numpy.ma.core.inspect`, which exposes Python's introspection utilities — including `sys.modules` — thereby providing access to unfiltered system-level functionality like `os.system`. This vulnerability affects the Agenta self-hosted platform (API server), not the SDK when used as a standalone Python library. The custom code evaluator runs server-side within the API process. The issue is fixed in v0.48.1 by removing `numpy` from the sandbox allowlist. In later versions (v0.60+), the RestrictedPython sandbox was removed entirely and replaced with a different execution model.

Published Feb 25, 2026 · Updated Oct 13, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP · CNA: GitHub_M

Low

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.

How the score was calculated

EPSS 0.7% (30-day exploitation probability)+8
Technical severity (critical)+10
CISA SSVC: exploitation "poc"+5

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation

Not confirmed

Not in CISA KEV — an absence of record, not proof it is unexploited.

EPSS FIRST

0.72%

ahead of 53% of scored CVEs · Oct 14, 2026

Affects

Agenta-AI

Agenta-api and 1 more

CVSS base

9.9

Critical · 3 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation

Proof of concept

none · proof-of-concept · active

Automatable

can an attacker script the kill-chain steps

Technical impact

Total

partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

No fix documented by the sources we poll. That does not mean none exists: check the vendor advisory.

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

Identify exposed assets running the affected vendor/product/version combinations (Agenta-AI Agenta-api, Agentatech Agenta).
No fix documented in the sources: reduce exposure and monitor the vendor advisory.
Search available logs for exploit probes matching the vulnerability class (injection), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

Vendor	Product	Versions	Status	Source
Agenta-AI	Agenta-api	version < 0.48.1	Vulnerable	CVE Program (cve.org) e CISA ADP
Agentatech	Agenta	< 0.48.1	Vulnerable	NIST National Vulnerability Database

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector

Network

Attack complexity

Low

Privileges required

Low

User interaction

None

Scope

Changed

Confidentiality

High

Integrity

High

Availability

High

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

Score	Version	Severity	Expl.	Impact	Scored by
9.9	CVSS 3.1	Critical	3.1	6.0	nvd@nist.gov via NIST National Vulnerability Database
8.8	CVSS 3.1	High	2.8	5.9	security-advisories@github.com via NIST National Vulnerability Database
8.8	CVSS 3.1	High	—	—	GitHub_M via CVE Program (cve.org) e CISA ADP

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H (score shown at the top: nvd@nist.gov)

Scoring entities (NIST, CNA, ADP) score independently; each score is shown with its origin. For prioritization we use 9.9 (NVD (NIST)) as a conservative provisional reference — not a definitive official score.

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-94 · Code Injection

Other CVEs with this weakness →

EPSS over time FIRST

Oct 13, 2026 → Oct 14, 2026 · 2 reading(s) · max 0.72%

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
Look for parameters with command/query metacharacters and unexpected child processes of the service.

web/proxy/WAF logsnetwork IDS/IPSapplication logsendpoint telemetry (EDR)

Timeline

What happened to this CVE, newest first.

2026
Affected products added · agenta-ai/agenta-api
Oct 13, 2026 · CVE Program (cve.org) e CISA ADP
SSVC assessment updated
Oct 13, 2026 · CVE Program (cve.org) e CISA ADP
Record published
Oct 13, 2026
CVSS changed · 9.9
Oct 13, 2026 · NIST National Vulnerability Database
Source status changed · → Analyzed
Oct 13, 2026 · NIST National Vulnerability Database
Record created in this database
Oct 13, 2026 · NIST National Vulnerability Database
CVE published
Feb 25, 2026 · GitHub_M

Source activity

Repeated readings are counted rather than listed.

1× Official description updated · Oct 13, 2026 – Oct 13, 2026

References

1 on the record

github.com/Agenta-AI/agenta/security/advisories/GHSA-pmgp-2m3v-34mq
Exploit, Vendor Advisory, x_refsource_CONFIRM, NIST National Vulnerability Database

Elsewhere on this site

Agenta-AI
every CVE for this vendor

Injection
same class

CWE-94
other pages naming this weakness

Related CVEs (same products)

High CVE-2026-27961 Agenta's Server-Side Template Injection (SSTI) via custom evaluator Jinja2 templates allows RCE Feb 25, 2026

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

No fixed version, patch or mitigation documented.
No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-27952 is "Agenta has Python Sandbox Escape, Leading to Remote Code Execution (RCE)", rated Critical. It affects Agenta-api (Agenta-AI); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 9.9 describes technical severity. EPSS 0.72% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.