CVE-2026-62676: Omnigent shell parser bypass lets agents evade git push and workspace policies
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-62676
- Published
- Record updated
- Affected
- omnigent < 0.3.0
- Fixed in
- 0.3.0
- released June 27, 2026, 55 days before disclosure
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.4%
Summary
Omnigent, an open-source AI agent framework and meta-harness for orchestrating coding agents, has a flaw in its shared shell-command parser (omnigent/policies/builtins/_shell.py) before version 0.3.0. The parser does not recognize combined interpreter flags, the timeout, nice, setsid, and stdbuf wrappers, command substitutions, or a single background control operator. A gated git push or gh write hidden in these forms yields no parsed operation, so the github.py write_repos and write_branches allowlist and the working_dir.py workspace confinement policies abstain and allow the command. An authenticated or prompt-injected agent can therefore push to an unauthorized repository or branch or escape the intended workspace (CVE-2026-62676).
Mitigation
Fixed in version 0.3.0.
Topics
Related items
- MediumCVE-2026-124248: GPTranslate WordPress plugin stored cross-site scripting via comment parameterSimilar attack · NVD/CVE Database
- MediumAmazon: China-Linked Hackers’ AI Agents Exploited Medical Software Zero-DaySimilar attack · SecurityWeek
- MediumAttackers' AI Agents Found a Zero-Day in Medical-Imaging Software and Gained Root AccessSimilar attack · The Hacker News
- MediumCVE-2026-54026: LibreChat message injection via conversationId in request bodySimilar attack · NVD/CVE Database
- MediumCVE-2026-54046: LibreChat unauthenticated account enumeration via /api/user/verifySimilar attack · NVD/CVE Database