PraisonAI recipe.run_stream skips dangerous-tool policy enforcement
CVE-2026-56838 · GHSA-v847-hxxw-3pxg · published 2026-06-18 · updated 2026-07-20
- Severity
- High
- CVSS score
- 7.8
- 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 operator runs an untrusted recipe through streaming mode, or exposes the recipe streaming API to users who can choose recipe names or URIs, the recipe can reach execution with default-denied tools even though the caller did not set allowdangeroustools=True. If the workflow reaches the approved execute_command tool call, commands run with the privileges of the PraisonAI process. The exact trigger depends on the workflow and model/tool-call path, but the dangerous-tool policy boundary is already bypassed before execution. The HTTP recipe sidecar is documented as a localhost REST API with SSE streaming and optional API-key/JWT authentication.
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.
Centralize recipe preflight enforcement so every execution mode uses the same guard: 1. Run checktoolpolicy(recipeconfig) in runstream() unless options["allowdangeroustools"] is true. 2. Perform that check before both dry-run and real execution, matching recipe.run(). 3. Prefer a shared helper for dependency checks, dangerous-tool policy checks, and dry-run handling so future entrypoints cannot drift. 4. Add regression tests: declared dangerous tool is denied by recipe.run(); the same declared dangerous tool is denied by recipe.runstream(); allowdangeroustools=True preserves the intended opt-in behavior; /v1/recipes/stream maps a policy denial to a non-success SSE event or
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| praisonai | PyPI | >= 4.5.87, <= 4.6.58 | 4.6.59 |
- CriticalUnauthenticated Remote Code Execution in Langflow via Public Flow Build EndpointlangflowExploited
- CriticalRay is vulnerable to Critical RCE via Safari & Firefox Browsers through DNS Rebinding AttackrayExploited
- CriticalLangflow Unauth RCElangflow, langflow-baseExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalMLflow vulnerable to remote code execution on unauthenticated servers via third-party scorer deserialization importing caller-placed artifacmlflow
- CriticalAgno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`agno
- 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.