Логотип exploitDog
Консоль
Логотип exploitDog

exploitDog

Количество 2

Количество 2

nvd логотип

CVE-2026-56075

3 месяца назад

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approval_mode to auto, overriding administrator configuration from PRAISON_APPROVAL_MODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary shell commands via subprocess.run with shell=True, bypassing the manual approval gate and insufficient command sanitization blocklists.

CVSS3: 8.8
EPSS: Низкий
github логотип

GHSA-gx4r-3wg8-9w5x

3 месяца назад

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approval_mode to auto, overriding administrator configuration from PRAISON_APPROVAL_MODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary shell commands via subprocess.run with shell=True, bypassing the manual approval gate and insufficient command sanitization blocklists.

CVSS3: 8.8
EPSS: Низкий

Уязвимостей на страницу

Уязвимость
CVSS
EPSS
Опубликовано
nvd логотип
CVE-2026-56075

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approval_mode to auto, overriding administrator configuration from PRAISON_APPROVAL_MODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary shell commands via subprocess.run with shell=True, bypassing the manual approval gate and insufficient command sanitization blocklists.

CVSS3: 8.8
1%
Низкий
3 месяца назад
github логотип
GHSA-gx4r-3wg8-9w5x

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approval_mode to auto, overriding administrator configuration from PRAISON_APPROVAL_MODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary shell commands via subprocess.run with shell=True, bypassing the manual approval gate and insufficient command sanitization blocklists.

CVSS3: 8.8
1%
Низкий
3 месяца назад

Уязвимостей на страницу