{"action":"No fix published. Pin and monitor.","affected":[{"introduced":"0","last_affected":"1.82.5"}],"component":"litellm","cve_ids":["CVE-2026-12797"],"ecosystem":"PyPI","epss":0.004,"exploited":false,"fixed_versions":[],"ghsa_id":"GHSA-p897-vf7j-f5h8","id":"tcs_01M5KH9PRK76WRPYWGMHZFQWX5","modified_at":"2026-10-01T17:45:12.788897601Z","published_at":"2026-10-01T16:38:27.585513Z","references":["https://osv.dev/vulnerability/PYSEC-2026-4074","https://nvd.nist.gov/vuln/detail/CVE-2026-12797","https://gist.github.com/YLChen-007/078179224f07cc4e39e4f141a18c817a","https://github.com/BerriAI/litellm","https://vuldb.com/cve/CVE-2026-12797","https://vuldb.com/submit/811288","https://vuldb.com/vuln/372559","https://vuldb.com/vuln/372559/cti","https://pypi.org/project/litellm","https://github.com/advisories/GHSA-p897-vf7j-f5h8"],"severity":{"label":"medium","score":6.3},"sources":[{"source":"osv","source_id":"PYSEC-2026-4074","url":"https://osv.dev/vulnerability/PYSEC-2026-4074"}],"summary":"BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async Endpoints"}