GitHub Advisoryadvisory · PyPI
GHSA-jrrm-9hc7-2v3h Omnigent: Shared Agent Bundle Overwrite Leads to Authenticated Runner RCE
CRITICAL
Official page ↗
- Aliases
- CVE-2026-62674
- Ecosystem
- PyPI
- Packages
- omnigent
- Severity
- Critical
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:H
- Weaknesses
- CWE-94
- Reviewed
- 2026-09-02
Affected packages
• PyPI omnigent: < 0.3.0 → fixed in 0.3.0
Description
Summary
An authenticated user with edit access to their own session can overwrite a shared/template agent by uploading a full agent bundle through `PUT /sessions/{session_id}/agent`.
Shared/template agents are shown as not MCP-editable, but this upload path still accepts a replacement bundle. By adding a `stdio` MCP server to the shared agent, the attacker can cause future runner sessions using that shared agent to start an attacker-controlled command.
Details
The vulnerable endpoint is the full agent bundle upload route: `PUT /sessions/{session_id}/agent`
This route checks whether the caller can edit the session: `LEVEL_EDIT` session permission check
But it does not check whether the bound agent is a shared/template agent.
Shared/template agents have:
```python
agent.session_id is None
```
The API already exposes that these agents are not meant to be MCP-editable: `mcp_servers_editable` is false for shared/template agents
The direct MCP edit endpoint correctly blocks shared/template agents: `session_mcp_servers.py` shared-agent guard
```python
if agent.session_id is None:
raise OmnigentError("Built-in agents are read-only through this endpoint.")
```
The full bundle upload endpoint is missing that same guard. It stores the uploaded bundle and updates the agent row: `agent_store.update(agent.id, new_loc)`
For shared/template agents, this changes the shared agent itself, not only the attacker's session.
This becomes command execution because `stdio` MCP servers start the configured command as a runner subprocess: `tools/mcp.py` stdio subprocess launch
Suggested fix: add the same `agent.session_id is None` guard to `PUT /sessions/{session_id}/agent`.
Impact
This is authenticated RCE against Omnigent runner hosts. A normal authenticated user with edit access to their own session can poison a shared/template agent bundle, even though that agent is shown as not MCP-editable. The poisoned bundle can then be used by future sessions created from the same shared agent.
Because `stdio` MCP servers run as local subprocesses, the attacker-controlled command executes with the permissions of the Omnigent runner process. In a shared or company-hosted deployment, this can let an attacker read runner-accessible files and credentials, modify workspace data, disrupt runner availability, pivot to internal services reachable from the runner, or establish an interactive remote shell if outbound networking is allowed.
This is high impact because it turns normal shared-agent session access into command execution on runner infrastructure used by other sessions.
Related
Alias · CVE (1)
- CVE-2026-62674 Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. vulnerability
Weakness · CWE (1)
- CWE-94 Improper Control of Generation of Code weakness
References
- https://github.com/omnigent-ai/omnigent/security/advisories/GHSA-jrrm-9hc7-2v3h web
- https://nvd.nist.gov/vuln/detail/CVE-2026-62674 advisory
- https://github.com/omnigent-ai/omnigent/pull/1418 web
- https://github.com/omnigent-ai/omnigent/commit/25a22dc9e6da4648d23749f0a589e47e6aed991b web
- https://github.com/omnigent-ai/omnigent package
- https://github.com/omnigent-ai/omnigent/releases/tag/v0.3.0 web