CVE-2026-113663

Read full description

AG2 is an open-source AgentOS. From 0.13.2 until ag2 1.1.1, and from autogen 0.13.2 to 0.14.1, SandboxShellTool configurations using allowed=[...] or readonly=True rely on ShellAdapter._filter and contains_shell_operator in ag2/tools/sandbox/filter.py and ag2/tools/sandbox/adapter/shell.py to validate a command prefix and reject selected shell syntax. The filter omits newline and carriage-return separators, while the accepted raw string is passed to sh -c, allowing an attacker-influenced agent command to execute an additional arbitrary statement. With the default LocalEnvironment backend, the injected statement runs as a host subprocess with the privileges of the agent process and can affect confidentiality, integrity, and availability. This issue is fixed in ag2 version 1.1.1.

CVSS 8.8 (HIGH)

Attention and evidence

HYPE SCORE

0.0/10

REALITY · THREAT PRIORITY

3.1–5.6/10

Missing inputs: range of priority

Evidence confidence: Insufficient evidence

Why this priority?

Technical severity: CVSS 8.8: +3.08

Fresh prediction unavailable

General review priority, not probability, victim count or asset-specific risk. A range covers missing CVSS/EPSS inputs within the current evidence state.

Sources: 1 documents and public datasets.

Hype components

Headline sample (25%)

0/100

Press, 30 days (60%)

0/100

Grounded branding (15%)

0/100

HYPE TOTAL0/100

Sources and documents

Latest Vulnerabilities

Technical advisory · 05 Nov 2026, 22:53 · CVE-2026-113663 - AG2: Newline injection in SandboxShellTool bypasses allowed=[...] and readonly=True, enabling arbitrary command execution

Score evolution

● Hype ● Reality

First record: hype 0.0 · reality 3.1 (2026-11-05 23:22). The curve appears once the score changes.

Public exploit evidence

Public exploit entries / repo candidates

Evidence context and dated references

Reality is general threat/review priority, combining observed exploitation, CVSS severity and fresh EPSS. Evidence confidence is separate. This is not calibrated risk, a victim count or an asset-specific assessment. A range reflects missing numeric inputs. Published 1 days ago. Exploitation evidence usually takes weeks to show up: a low reality score can mean there is no data yet, not that the flaw is mild.

Evidence in context

Confidence in exploitation evidence: Insufficient evidence
Priority basis: Exploitation in attacks unconfirmed; CVSS 8.8; fresh prediction unavailable
Attention, last 30 days: 0 distinct story titles; 0 press documents; 0 publisher domains.
Technical potential: network access, low privileges, no user interaction.
Observed activity: No exploitation observation is recorded.
Known scale: Not quantified.
Evidence confidence basis: Insufficient evidence

Score evaluated: 2026-11-05 23:22:13.554442+00:00 · EPSS snapshot: not available

Source event timeline

Published

05 Nov 2026, 22:53

Score calculated

05 Nov 2026, 23:22