PraisonAI DiscordApproval accepts unrelated channel messages as dangerous-tool approvals
CVE-2026-56832 · GHSA-8579-rgg5-ph2m · published 2026-06-18 · updated 2026-07-20
- Severity
- High
- CVSS score
- 8.8
- Chance of exploitation (EPSS)
- 0.15%
- Fixed in
- 4.6.59
- Exploitation Public proof of concept
- Automatable No
- Technical impact Total
- CISA SSVC
If an application uses DiscordApproval for dangerous tools such as shell commands, file writes, deletes, deployments, or other privileged operations, a low-privileged Discord user with write access to the configured approval channel can approve pending dangerous tool executions. This can lead to code execution, file modification, deployment changes, or data access with the privileges of the PraisonAI process, depending on which tools the agent exposes behind approval. The attacker does not need the LLM API key, shell access, repository access, or PraisonAI process access.
Upgrade praisonai to 4.6.59 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
Recommended fixes: 1. For Discord, require approvals to be tied to the request, not merely any later channel message. Use Discord interactions/buttons with opaque server-side request ids, or require a Discord reply whose messagereference.messageid matches the approval message. 2. Add explicit approver identity configuration to all messaging approval backends, for example approveruserids or allowed_approvers. 3. Reject approvals from users outside the configured approver set, even if the message appears in the configured channel. 4. Include a per-request nonce or opaque approval id in callbacks and verify it server side before returning ApprovalDecision(approved=True). 5.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| praisonai | PyPI | >= 4.5.2, <= 4.6.58 | 4.6.59 |
- CriticalMarimo: Pre-Auth Remote Code Execution via Terminal WebSocket Authentication BypassmarimoExploited
- CriticalLangflow CORS misconfiguration enables Account Takeover and RCElangflowExploited
- HighLiteLLM: MCP Authentication Bypass via OAuth2 Passthrough FallbacklitellmExploited
- HighLangflow: IDOR Vulnerability in `/api/v1/responses` Endpoint Allows Authenticated Attackers to Access Another User's FlowlangflowExploited
- CriticalTodoist MCP Server: Browser DNS rebinding lets websites write and delete Todoist data through local MCP server@doist/todoist-mcp
- CriticalLangflow: Unauthenticated Flow Execution via Webhook Authentication Bypasslangflow
- CriticalPraisonAI: AICoder Arbitrary File Write and Command Execution via LLM Tool Callspraisonai
- CriticalPraisonAI: Code Injection via f-string Interpolation in Deploy API Server Generationpraisonai
- CriticalPraisonAI has a Browser Server WebSocket origin validation bypass via unanchored regex (patch bypass of CVE-2026-40289 / GHSA-8x8f-54wf-vv92praisonai
- CriticalPraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validationpraisonai
- CriticalPraisonAI: Unauthenticated RCE via Jobs API + Approval Bypasspraisonaiagents, praisonai
- CriticalPraisonAI: AgentOS remains unauthenticated after incomplete fix version and allows remote agent invocationpraisonai
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.