PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation
CVE-2026-57145 · GHSA-29w3-p9w9-wc47 · published 2026-06-18 · updated 2026-07-20
- Severity
- Critical
- CVSS score
- 9.1
- Chance of exploitation (EPSS)
- 0.54%
- Fixed in
- 4.6.61
- Exploitation No known exploitation
- Automatable Yes
- Technical impact Total
- CISA SSVC
An attacker who can influence the filepath parameter of the multiedit tool (via crafted prompts to an AI agent, user messages in Telegram/Discord/Slack bots using auto_approve_tools=True, or YAML workflow configurations) can: Read arbitrary files — any file readable by the process user, including secrets, SSH keys, cloud credentials, environment files (.env), and configuration files. Write/overwrite arbitrary files — modify any file writable by the process user, enabling privilege escalation (e.g., writing to ~/.bashrc, ~/.ssh/authorized_keys, or overwriting application source code). …
Upgrade praisonai to 4.6.61 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.
Apply the same path validation pattern used by file_tools.py and the code tools in src/praisonai/praisonai/code/tools/: 1. Add a _validate_path function that: Rejects paths containing .. Resolves symlinks via os.path.realpath Validates the resolved path is within the workspace/CWD using os.path.commonpath 2. Add protected path guards (.env, .git, .ssh, keys, credentials) 3. Apply _validate_path to the filepath parameter before any open() call 4. Consider adding @require_approval(risk_level="high") to the multiedit function
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| praisonai | PyPI | < 4.6.61 | 4.6.61 |
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: Unauthenticated RCE via Jobs API + Approval Bypasspraisonaiagents, praisonai
- CriticalPraisonAI: AgentOS remains unauthenticated after incomplete fix version and allows remote agent invocationpraisonai
- CriticalPraisonAI: Jobs API exposes agent-execution endpoints with no authenticationpraisonai
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.