EUVD-2026-44637
GHSA-r3xw-gcpr-rf26
Severity by source
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:N/VI:H/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Local vector and required user interaction reflect session-scope exploitation with mandatory initial approval; PR:N because no OS account privileges are needed to influence agent arguments; I:H for arbitrary file write capability.
Primary rating from Vendor (VulnCheck).
CVSS VectorVendor: VulnCheck
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:N/VI:H/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Lifecycle Timeline
2DescriptionCVE.org
PraisonAI before 1.6.78 caches tool approval decisions by tool name only, allowing attackers to reuse initial approvals for subsequent calls with arbitrary arguments. Attackers can exploit this by obtaining approval for a benign operation and then executing dangerous file write operations with unreviewed parameters in the same session.
AnalysisAI
PraisonAI's tool approval caching mechanism in versions before 1.6.78 allows an attacker who influences an AI agent's behavior within a session to bypass human-in-the-loop oversight by reusing a single user-granted approval across tool calls with entirely different, unreviewed arguments. The flaw (CWE-863: Incorrect Authorization) directly undermines the security boundary that tool approval is designed to enforce, enabling arbitrary file write operations after approval of a benign operation. …
Unlock full vulnerability intelligence
- Risk assessment & exploitation conditions
- Attack chain visualization
- Remediation with exact patch versions
- Threat intelligence from 22 sources
- Personal watchlist & email alerts
Free forever · No credit card required
Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata
Vulnerability AssessmentAI
| Exploitation | Exploitation requires that: (1) the target deployment runs PraisonAI in a version earlier than 1.6.78 with the tool approval caching feature active; (2) a legitimate user has granted approval for at least one invocation of the targeted tool by name within the current session - this is the mandatory user interaction prerequisite reflected in the CVSS UI:P metric; and (3) the attacker can influence the AI agent's tool call argument construction within that same session, most practically through prompt injection or adversarial user inputs. … Additional conditions and limiting factors are described in the full assessment. |
| Risk Assessment | The CVSS 4.0 vector (AV:L/AC:L/AT:N/PR:N/UI:P/VC:N/VI:H/VA:L) places this squarely in the local-interaction threat model: exploitation is constrained to an active session and requires that a legitimate user has already granted at least one tool approval (UI:P). … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in. |
| Exploit Scenario | An attacker with the ability to inject adversarial instructions into an AI agent's prompt within a PraisonAI session first engineers the agent to request a harmless invocation of a file-writing tool - for example, writing to a temporary log path - and waits for the user to approve it. With the tool name now cached as approved, the attacker then crafts a second agent action using the same tool name but targeting a sensitive file path with malicious content, which executes immediately without any additional user review. … |
| Remediation | Upgrade PraisonAI to version 1.6.78 or later, which corrects the approval cache to evaluate tool name and argument payload together, preventing approval reuse across distinct invocations. … Detailed patch versions, workarounds, and compensating controls in full report. |
Threat intelligence, references, and detailed analysis are available after sign-in.
Remote code execution in PraisonAI before 1.6.78 allows attackers to run arbitrary Python on the host by manipulating th
Root-level command execution and arbitrary file write in PraisonAI's AICoder component (all versions before 4.6.78) let
Path traversal in PraisonAI multi-agent teams system (versions prior to 4.5.128) enables arbitrary file overwrite throug
Remote code execution in PraisonAI before 4.6.78 lets an attacker who can supply the agents_file parameter to deploy/api
SQL/CQL injection in PraisonAI's PGVector and Cassandra knowledge-store backends before 4.6.78 allows a caller who contr
PraisonAI AgentOS prior to version 4.5.128 exposes agent metadata including names, roles, and system instruction snippet
Remote code execution in PraisonAI multi-agent framework (versions prior to 4.5.128) allows unauthenticated attackers to
Unauthenticated remote session hijacking in PraisonAI's browser bridge (versions <4.5.139) and praisonaiagents (<1.5.140
Unauthenticated agent access in PraisonAI before 1.7.3 lets remote attackers read agent instructions and system prompts
Webhook signature-verification bypass in PraisonAI before 4.6.78 lets unauthenticated attackers forge Svix 'message.rece
Authentication bypass in PraisonAI before 4.6.78 lets a remote, unauthenticated attacker reach the Call API agent-invoca
System prompt extraction and unauthorized tool invocation in PraisonAI before 4.6.78 arise because the prompt-injection
Same weakness CWE-863 – Incorrect Authorization
View allSame technique Authentication Bypass
View allShare
External POC / Exploit Code
Leaving vuln.today