CriticalVulnerability
CVE-2024-23730: LlamaHub OpenAPI and ChatGPT plugin loaders allow code execution via YAML
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2024-23730
- Published
- Record updated
- Affected
- llama-hub < 0.0.67
- Fixed in
- 0.0.67
- released January 7, 2024, 14 days before disclosure
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 1.2%
Summary
CVE-2024-23730 affects the OpenAPI and ChatGPT plugin loaders in LlamaHub (aka llama-hub) before 0.0.67. Because safe_load is not used for YAML, attackers can execute arbitrary code. NVD has not yet provided an assessment, and the weakness is listed as NVD-CWE-noinfo.
Mitigation
Fixed in 0.0.67. The source references the v0.0.67 CHANGELOG, a pull request commit (pull/841), and the v0.0.67 release tag as patch and release notes.
Related items
- MediumGHSA-8prr-f582-jqq3: LangGraph CLI prints the registry push token in `langgraph deploy --verbose` outputSame vendor · GitHub Advisory Database
- HighGHSA-4hm6-w6qq-w73v: LangGraph JavaScript custom authentication may permit cross-user Store accessSame vendor · GitHub Advisory Database
- MediumGHSA-3fx2-cqw9-xr3c: LangGraph: Unencoded identifiers in LangGraph SDK v3 streaming can redirect authenticated GET requestsSame vendor · GitHub Advisory Database
- MediumGHSA-6hmw-9432-67qq: LangGraph: Namespace labels containing `.` reach other namespaces in Postgres and SQLite storesSame vendor · GitHub Advisory Database
- MediumCVE-2026-108575: BerriAI LiteLLM improper authorization in secret resolution via api_keySame vendor · NVD/CVE Database