CVE-2026-56074Medium· 5.5▾ TwilightPoC availablePraisonAI 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 …
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 30.3 · likelihood 0 · exploitation 12
A public proof-of-concept already exists for this vulnerability — see Exploit availability below.
Stakeholder-Specific Vulnerability Categorization from CISA's ADP record at CVE.org: whether exploitation is observed, whether an attack can be automated, and how much of the system is at stake.
Exploit-prediction probability, daily snapshots since Jul 30.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
0.2%
Last analysed / modified upstream
Exploit / PoC code exists
0.2% → 0.2%
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.
Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Affected packages:
praisonaiagents < 4.5.128Patched in:
praisonaiagents 4.5.128Field changes observed since this record was first indexed.
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-56075High· 8.8PraisonAI 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
GHSA-x44p-gg67-52fcMedium· 5.5Duplicate Advisory: PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell Commands
CVE-2026-56839High· 7.3PraisonAI is a multi-agent teams system
CVE-2026-57117High· 8.8PraisonAI: Compute-bridged file tools allow shell command injection
CVE-2026-56838High· 7.8PraisonAI recipe.run_stream skips dangerous-tool policy enforcement
CVE-2026-56835High· 8.3PraisonAI Slack app_mention bypasses configured user/channel authorization