PraisonAI Code agent tools fail open without a workspace boundary
CVE-2026-56839 · GHSA-gcq3-mfvh-3x25 · published 2026-06-18 · updated 2026-07-20
- Severity
- High
- CVSS score
- 7.3
- Chance of exploitation (EPSS)
- 0.38%
- Fixed in
- 4.6.59
- Exploitation Public proof of concept
- Automatable No
- Technical impact Total
- CISA SSVC
If an application exposes PraisonAI Code's agent-compatible CODETOOLS to an LLM before setting a workspace boundary, prompt-influenced tool calls can read and modify files outside the intended project workspace. The practical attack shape matches the existing PraisonAI prompt-content advisory pattern: untrusted content influences an agent that has been given file-editing tools.
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 fix: 1. Make every low-level file helper compute . 3. Keep allowing absolute paths only when they resolve inside the effective workspace. 4. Add regression tests proving outside absolute paths are rejected before and after setworkspace(). 5. Consider failing closed if CODETOOLS is used before a workspace is configured, or log a warning when the default current working directory is used.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| praisonai | PyPI | <= 4.6.57 | 4.6.59 |
1 registered MCP server installs an affected version today, by the dependency versions a fresh install resolves.
- io.github.MervinPraison/praisonaipraisonai@2.3.42
- CriticalMCP Path Traversal Allows Full-Filesystem Read and JWT Secret Exfiltration Leading to Account Takeoverlangflow, langflow-base
- Critical@zereight/mcp-gitlab: Unauthenticated arbitrary file read via `upload_markdown` enables PAT exfiltration and full account takeover@zereight/mcp-gitlab
- CriticalFlowise RCE via SQL Database Chain Nodeflowise, flowise-components
- CriticalLangroid: SQLChatAgent dangerous-function blocklist can be bypassed with quoted or schema-qualified pg_read_file callslangroid
- Criticalfast-mcp-telegram: Bearer token path traversal bypasses reserved Telegram session protectionfast-mcp-telegram
- CriticalMCP Toolbox HTTP tool path parameters allow traversal to unintended endpointsgithub.com/googleapis/mcp-toolbox
- 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.