Threat Intelligence Database

Omnigent is an open-source AI agent framework and meta-harness for orchestrating coding agents. Prior to 0.3.0, an authenticated user can upload a session-scoped agent bundle with an absolute or traversal-containing os_env.cwd value because omnigent/spec/parser.py stores the value verbatim and omnigent/spec/validator.py does not constrain it. On a runner where OMNIGENT_RUNNER_WORKSPACE is unset, omnigent/runner/resource_registry.py preserves the attacker-controlled path and omnigent/inner/os_env.py uses the resolved path as the environment root and copytree source. The _assert_within_cwd check then treats that attacker-selected root as trusted, allowing sys_os_read, write, edit, and shell tools to access runner files and environment secrets outside the intended workspace. This issue is fixed in version 0.3.0.

Omnigent versions prior to 0.3.0 contain a vulnerability in the shared shell-command parser that fails to recognize certain combined interpreter flags and command wrappers. This parsing failure causes security policies to abstain from enforcing restrictions, allowing authenticated or prompt-injected agents to push to unauthorized repositories or branches or escape workspace confinement. The issue is fixed in version 0.3.0.

CVE-2026-62674 is a critical code injection vulnerability in the omnigent open-source AI agent framework. Before version 0.3.0, the PUT /sessions/{session_id}/agent endpoint improperly allows an authenticated user with edit permissions to replace a shared or template agent with agent.session_id set to None. This flaw enables execution of attacker-controlled commands with the permissions of the Omnigent runner process, potentially exposing sensitive files, credentials, workspace data, internal services, and affecting runner availability. The issue is fixed in version 0.3.0.