AG2: Newline injection in SandboxShellTool bypasses allowed=[...] and readonly=True, enabling arbitrary command execution
CVE-2026-113663 · GHSA-2h4w-29cv-2cmv · published 2026-11-10
- Severity
- High
- CVSS score
- 8.8
- Chance of exploitation (EPSS)
- 0.35%
- Fixed in
- 1.1.1
- Exploitation No known exploitation
- Automatable No
- Technical impact Total
- CISA SSVC
Any agent configured with SandboxShellTool(allowed=[...]) or SandboxShellTool(readonly=True) — the two configurations the tool's own docstring presents as actual security boundaries, as opposed to blocked, which the same docstring explicitly says "is not a security boundary" — can be made to execute arbitrary shell commands via a single embedded newline in the command argument. Because tool arguments are LLM-generated and can be steered by content the agent processes (a fetched document, tool output, or any other text reaching the model — i.e. indirect prompt injection), this is reachable without the operator of the agent writing the malicious command themselves. …
Upgrade ag2 to 1.1.1 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
Add "\n" and "\r" to _SHELL_OPERATORS in ag2/tools/sandbox/filter.py so contains_shell_operator() rejects embedded newlines the same way it rejects ;. - More robustly, execute allowlisted/readonly commands without invoking a shell in restricted mode (shlex.split + exec with no sh -c wrapper), so redirection, chaining, substitution, and every kind of statement separator are inert by construction instead of relying on an enumerated denylist.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| ag2 | PyPI | >= 0.13.2, < 1.1.1 | 1.1.1 |
- CriticalUnauthenticated Remote Code Execution in Langflow via Public Flow Build EndpointlangflowExploited
- CriticalRay is vulnerable to Critical RCE via Safari & Firefox Browsers through DNS Rebinding AttackrayExploited
- CriticalLangflow Unauth RCElangflow, langflow-baseExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalMLflow vulnerable to remote code execution on unauthenticated servers via third-party scorer deserialization importing caller-placed artifacmlflow
- CriticalAgno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`agno
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.