CVE-2026-56402

CVE-2026-56402 affects NanoClaw prior to 2.1.17. The issue is in handleApprovalsResponse where responder role authorization is not verified, allowing attackers with a valid questionId to approve or reject privileged actions (e.g., package installation) without proper role validation. The vulnerab...

CVE-2026-56402 NanoClaw < 2.1.17 - Privilege Escalation via Unverified Approval Response Handler

NanoClaw before 2.1.17 contains a privilege escalation vulnerability in the handleApprovalsResponse function that fails to verify responder role authorization. Attackers with a valid questionId can approve or reject privileged actions like package installation by submitting approval response...

CVE-2026-56402 NanoClaw < 2.1.17 - Privilege Escalation via Unverified Approval Response Handler

NanoClaw before 2.1.17 contains a privilege escalation vulnerability in the handleApprovalsResponse function that fails to verify responder role authorization. Attackers with a valid questionId can approve or reject privileged actions like package installation by submitting approval response...

EUVD-2026-38233

A flaw was found in the Windows Machine Config Operator WMCO for Red Hat OpenShift Container Platform. The WICD CSR auto-approver validates that a Certificate Signing Request contains the organization system:wicd-nodes but does not reject additional organization values such as system:masters. A...

CVE-2025-66389

GitHub Copilot 1.372.0 is affected. The flaw allows filesystem access outside the workspace folder via a file-handler URI parameter to fetch_webpage, without user approval. This could enable exfiltration if an indirect prompt injection occurs. The CVSS 3.1 base score is 7.5 (HIGH) with network at...

GHSA-MXJX-28VX-XJJJ Network-AI: ApprovalInbox HTTP server has no authentication — anyone can approve pending agent actions

Summary network-ai's ApprovalInbox lib/approval-inbox.ts is a shipped, exported, documented feature — "a web-accessible approval queue with REST API … and SSE streaming" SECURITY.md. It is the network surface of the human-in-the-loop Approval Gate, which ApprovalGate uses to require explicit huma...

GHSA-JV2H-4P9V-WF5W ouroboros-ai: Incomplete fix of CVE-2026-47211: untrusted project .env can still reach RCE via omitted execution-routing keys

Impact The CVE-2026-47211 fix 0.39.0 added UNTRUSTEDENVDENYLIST to stop an untrusted project-directory .env from redirecting execution. The denylist was incomplete — several execution-routing keys of the same RCE class were omitted, so a malicious cloned repo can still reach arbitrary command...

EUVD-2026-37958

PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent executecommand calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and...

EUVD-2026-37959

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approvalmode to auto, overriding administrator configuration from PRAISONAPPROVALMODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary...

GHSA-X44P-GG67-52FC Duplicate Advisory: PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell Commands

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-ffp3-3562-8cv3. This link is maintained to preserve external references. Original Description PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing...

CVE-2026-56075

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approvalmode to auto, overriding administrator configuration from PRAISONAPPROVALMODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary...

CVE-2026-56074

PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent executecommand calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and...

CVE-2026-56075

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approvalmode to auto, overriding administrator configuration from PRAISONAPPROVALMODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary...

CVE-2026-56075 PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approvalmode to auto, overriding administrator configuration from PRAISONAPPROVALMODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary...

CVE-2026-56075

PrasionAI before 4.5.128 contains an arbitrary shell command execution vulnerability in which UI modules hardcode approval_mode to auto, overriding the PRAISON_APPROVAL_MODE environment variable. This allows authenticated attackers to instruct the LLM agent to run arbitrary commands via subproces...

CVE-2026-56075 PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approvalmode to auto, overriding administrator configuration from PRAISONAPPROVALMODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary...

CVE-2026-56074

PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent executecommand calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and...

CVE-2026-56074

PraxionAI before 1.5.128 caches tool approval decisions by tool name rather than invocation arguments, enabling bypass of approval prompts for subsequent execute_command calls. Attackers could obtain initial approval for a benign command and then exfiltrate API keys and credentials via later shel...

PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml

Summary PraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allowdangeroustools=True. That policy only checks tools declared in TEMPLATE.yaml requires.tools. For steps-based recipes, the actual execution path...

Incorrect Authorization

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...