How severe is CVE-2026-56074?

CVE-2026-56074 has a CVSS 3.x base score of 5.5, rated medium severity. It is exploitable over local access with low attack complexity, requires no privileges and user interaction. Impact on confidentiality is high, integrity none, and availability none.

Is CVE-2026-56074 being actively exploited?

It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (2nd percentile), an estimate of the probability of exploitation in the next 30 days.

How do I fix CVE-2026-56074?

Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.

Does CVE-2026-56074 have an EU (EUVD) identifier?

Yes. CVE-2026-56074 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-37958.

When was CVE-2026-56074 published?

CVE-2026-56074 was published on 2026-06-18 and last updated on 2026-06-22.

CVE-2026-56074

CVE-2026-56074 is a medium-severity vulnerability with a CVSS 3.x base score of 5.5. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-863.

Key facts

Severity: Medium (CVSS 3.x base score 5.5)
CVSS v4: 6.8
EPSS exploit prediction: 0% (2nd percentile)
Actively exploited: Not listed in CISA KEV
EU (EUVD) id: EUVD-2026-37958
Weakness: CWE-863
Published: 2026-06-18
Last modified: 2026-06-22

Description

PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent execute_command calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and credentials via subsequent shell commands without user consent.

Frequently asked questions

What is CVE-2026-56074?: PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent execute_command calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and credentials via subsequent shell commands without user consent.
How severe is CVE-2026-56074?: CVE-2026-56074 has a CVSS 3.x base score of 5.5, rated medium severity. It is exploitable over local access with low attack complexity, requires no privileges and user interaction. Impact on confidentiality is high, integrity none, and availability none.
Is CVE-2026-56074 being actively exploited?: It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (2nd percentile), an estimate of the probability of exploitation in the next 30 days.
How do I fix CVE-2026-56074?: Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.
Does CVE-2026-56074 have an EU (EUVD) identifier?: Yes. CVE-2026-56074 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-37958.
When was CVE-2026-56074 published?: CVE-2026-56074 was published on 2026-06-18 and last updated on 2026-06-22.

References

Other CWE-863 (Incorrect Authorization) vulnerabilities

CVE-2026-48286 — Critical (CVSS 10.0): Adobe Campaign Classic (ACC) versions 7.4.3 build 9396 and earlier are affected by an Incorrect Authorization…
CVE-2026-48303 — Critical (CVSS 10.0): Adobe Campaign Classic (ACC) versions 7.4.3 build 9394 and earlier are affected by an Incorrect Authorization…
CVE-2026-44330 — Critical (CVSS 10.0): free5GC is an open-source implementation of the 5G core network. Prior to 4.2.2, free5GC's NEF mounts the…
CVE-2026-46595 — Critical (CVSS 10.0): Previously, CVE-2024-45337 fixed an authorization bypass for misused ssh server configurations; if any other type of…
CVE-2026-33105 — Critical (CVSS 10.0): Improper authorization in Microsoft Azure Kubernetes Service allows an unauthorized attacker to elevate privileges over…
CVE-2026-32213 — Critical (CVSS 10.0): Improper authorization in Azure AI Foundry allows an unauthorized attacker to elevate privileges over a network.

Browse all CWE-863 (Incorrect Authorization) vulnerabilities →