PraisonAI: [Path Traversal] agent tools escape the configured workspace via symlinks
CVE-2026-55540 · GHSA-ch89-h4r2-c8f8 · published 2026-08-25
- Severity
- High
- CVSS score
- 7.1
- Chance of exploitation (EPSS)
- 0.39%
- Fixed in
- 4.6.58
- Exploitation Public proof of concept
- Automatable No
- Technical impact Total
- CISA SSVC
Confidentiality: read files outside the workspace (in-workspace symlink; or list/enumerate outside dirs via listfiles). Integrity: overwrite outside files via symlink; create/modify files outside the workspace via executecommand running in an escaped cwd. Execution boundary: run arbitrary available binaries (argv-controlled) from a directory outside the workspace. Bounded by the process user's permissions. In a code-agent or server-exposed agent processing untrusted input, this exposes secrets / project-adjacent / host files and breaks the project-boundary integrity guarantee the workspace setting advertises.
Upgrade praisonai to 4.6.58 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.
Replace ispathwithindirectory() with a realpath() / Path.resolve()-based containment check, and compare with os.path.commonpath() rather than startswith. Apply that check consistently to every file path, directory path, backup path, diff/search-replace target, and command working directory, after full canonicalization (resolve the symlink's real target, not the link path). executecommand(): validate cwd containment when workspace is set; codeexecutecommand() should pass workspaceroot to the low-level helper or validate itself.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| praisonai | PyPI | < 4.6.58 | 4.6.58 |
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.