Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍
🐍 PyPI
Not in CISA KEV
MEDIUM severity

GHSA-p897-vf7j-f5h8

MEDIUM

GHSA-p897-vf7j-f5h8 is a medium-severity (CVSS 6.3) CWE-285 vulnerability in litellm. O3 Security confirms whether GHSA-p897-vf7j-f5h8 is actually reachable in your code before you act, and blocks exploitation at runtime until you patch.

BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async Endpoints

Also known asCVE-2026-12797
Published
Jun 21, 2026
Updated
Sep 14, 2026
Affected
1 pkg
Patched
None yet
Exploits
None indexed
Exploitation data as of Sep 14, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

Proof-of-concept exploit code exists

  • CISA’s SSVC triage found public proof-of-concept exploit code for this CVE, though no confirmed active exploitation.

Exploitation and automatability from CISA’s SSVC triage for GHSA-p897-vf7j-f5h8.

Real-World Exposure

1 pkg affected
🐍litellm

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

A security flaw has been discovered in BerriAI litellm up to 1.82.5. Affected is the function async_pre_call_hook of the file enterprise/enterprise_hooks/banned_keywords.py of the component Completions Interface. The manipulation of the argument prompt results in incorrect authorization. The attack may be performed from remote. The exploit has been released to the public and may be used for attacks. The vendor was contacted early about this disclosure.

Affected Packages

1 total
EcosystemPackageVulnerable rangeFix
🐍PyPIlitellmall versionsNo fix

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for litellm. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.

  2. Remediation status

    No patched version of litellm has shipped for GHSA-p897-vf7j-f5h8 yet. Where your build allows, override or pin the dependency away from the vulnerable range, and apply any maintainer-recommended mitigation.

  3. Mitigate without a patch

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

  4. How O3 protects you

    O3 pinpoints whether GHSA-p897-vf7j-f5h8 is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Tailored to GHSA-p897-vf7j-f5h8. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

A security flaw has been discovered in BerriAI litellm up to 1.82.5. Affected is the function async_pre_call_hook of the file enterprise/enterprise_hooks/banned_keywords.py of the component Completions Interface. The manipulation of the argument prompt results in incorrect authorization. The attack may be performed from remote. The exploit has been released to the public and may be used for attacks. The vendor was contacted early about this disclosure.
O3 Security · Impact-Aware SCA

Is GHSA-p897-vf7j-f5h8 in your dependencies?

O3 detects GHSA-p897-vf7j-f5h8 across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.

GHSA-p897-vf7j-f5h8: litellm (Medium 6.3) | O3 Security