Severity by source
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Local vector (AV:L) and required user interaction (UI:R) because the victim must load the crafted command file; attacker needs no privileges on the target system.
Primary rating from Vendor (VulnCheck).
CVSS VectorVendor: VulnCheck
Lifecycle Timeline
1DescriptionCVE.org
PraisonAI before 4.6.78 fails to validate file path references in custom command templates, allowing attackers to read files outside the workspace. Attackers can include path traversal sequences like @../outside_secret.txt or absolute paths in project command files to exfiltrate process-readable files into model prompts.
AnalysisAI
Path traversal in PraisonAI before 4.6.78 enables file exfiltration outside the workspace by embedding traversal sequences (e.g., @../outside_secret.txt) or absolute paths in custom project command templates, which are then injected verbatim into model prompts. Users who process attacker-controlled command files expose all process-readable files - including credentials, environment variables, and application secrets - to whoever controls the model interaction. No public exploit code has been identified and PraisonAI is not listed in the CISA KEV catalog at time of analysis; a vendor patch is available.
Technical ContextAI
PraisonAI is an open-source multi-agent AI orchestration framework (CPE: cpe:2.3:a:mervinpraison:praisonai:*:*:*:*:*:*:*:*) that allows users to define project-level command templates referencing local files via an @filename syntax. CWE-22 (Improper Limitation of a Pathname to a Restricted Directory - Path Traversal) identifies the root cause: the template parser accepts user-supplied path references without canonicalizing or bounding them to the workspace directory. As a result, sequences like @../../../etc/shadow or absolute paths like /home/user/.ssh/id_rsa are resolved against the host filesystem at the process's permission level, and the resolved file contents are silently folded into the prompt context sent to the underlying model.
RemediationAI
Upgrade PraisonAI to version 4.6.78 or later, which incorporates the fix from commit 3aa9cbc2bd49c23a32be0a89a5e620d13d843eab (https://github.com/MervinPraison/PraisonAI/commit/3aa9cbc2bd49c23a32be0a89a5e620d13d843eab). The vendor advisory at https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-xpx6-x8c2-mw5w should be consulted for release guidance. As a compensating control before patching, restrict the OS-level file permissions of sensitive files (credentials, key material, .env files) so they are not readable by the user or service account running PraisonAI - note this reduces the blast radius but does not eliminate the path traversal flaw. Additionally, avoid processing project command files from untrusted or unreviewed sources; auditing command templates for @.. or absolute-path references can identify malicious files before execution.
WebSocket origin-validation bypass in PraisonAI's Browser Server (praisonai/browser/server.py) before 4.6.58 lets an att
PraisonAI's `praisonai serve` subsystem (agents and unified modes) accepts an `--api-key` CLI flag that is parsed but ne
Unauthenticated remote agent invocation in PraisonAI versions 4.6.34 through 4.6.57 allows any network-reachable caller
SSRF protection bypass in PraisonAI's praisonaiagents library (all versions before 1.6.58) lets low-privileged users rou
Authentication fail-open in PraisonAI's Recipe HTTP server allows unauthenticated remote attackers to invoke recipe exec
Authentication bypass in PraisonAI's AgentServer component exposes all routes - /publish, /events, /info, /health - to u
Arbitrary Python code execution in PraisonAI's workflow include feature allows an attacker who controls a local recipe d
Server-side request forgery in PraisonAI's web_crawl() function (versions 1.5.128-1.6.57) allows an attacker who can inf
Cross-site request forgery against the PraisonAI MCP HTTP-stream transport allows unauthenticated remote attackers to ex
Remote unauthenticated access to PraisonAI's legacy Flask API server allows attackers to execute configured agent workfl
Path traversal in praisonaiagents prior to 1.6.58 allows a low-privileged caller to write arbitrary JSON files to any pr
Server-Side Request Forgery in PraisonAI before version 4.6.58 allows unauthenticated remote attackers to force the appl
Same weakness CWE-22 – Path Traversal
View allSame technique Path Traversal
View allShare
External POC / Exploit Code
Leaving vuln.today
EUVD-2026-43174
GHSA-wgvq-3jxh-4qg7