CVE-2026-61445
Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.
NVD · uneditedPraisonAI before 4.6.78 contains arbitrary file write and command execution vulnerabilities in the AICoder component due to missing path validation and command sanitization in LLM tool calls. Attackers can inject malicious prompts through the chat interface to write files to arbitrary filesystem locations and execute arbitrary shell commands with root privileges.
Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.
dbcve analysis · high confidencePraisonAI before 4.6.78 has critical vulnerabilities in the AICoder component where missing path validation and lack of command sanitization in LLM tool calls allow attackers to inject malicious prompts via the chat interface to write files to arbitrary filesystem locations and execute arbitrary shell commands with root privileges.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.
From the vector- Attack vector
- Network
- Complexity
- Low
- Privileges
- Low
- User interaction
- None
- Scope
- Changed
- Confidentiality
- High
- Integrity
- High
- Availability
- High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.
dbcve checksWork through these to decide whether this CVE applies to you.
-
Confirm PraisonAI installationRun 'pip show praisonai' or check your package manager for the praisonai package installation statusAffected if PraisonAI is not installed or the package cannot be found
-
Determine installed PraisonAI versionRun 'pip show praisonai' and note the Version field, or check package.json/package-lock.json if installed from sourceAffected if Version is present and less than 4.6.78 (e.g., 4.6.77, 4.6.0, etc.)
-
Identify if AICoder component is activeCheck your PraisonAI configuration files (e.g., config.yaml, settings.json) or runtime logs for references to 'AICoder' or 'aicoder' module being loaded or usedAffected if AICoder component is configured, enabled, or appears in active logs
-
Verify LLM tool integration is configuredExamine your environment configuration for LLM provider settings (e.g., OPENAI_API_KEY, ANTHROPIC_API_KEY, or other LLM credentials) and check if tool_call or function_calling features are enabled in the AICoder settingsAffected if LLM integration is configured and tool execution is permitted in AICoder
-
Inspect file write permissions in chat interfaceIf you have access, test the chat interface by attempting a prompt that would trigger file writing (e.g., asking to write a file to /tmp/) and verify if path validation is absent or if arbitrary paths are acceptedAffected if The system allows writing files to locations outside intended directories without path validation
You are affected if PraisonAI version is below 4.6.78 AND the AICoder component is enabled with LLM tool call functionality configured, allowing unauthenticated prompt injection via the chat interface to write files or execute commands.
Generated from the published advisory. Verify against your own configuration.
Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.
From vendor dataUpgrade to PraisonAI version 4.6.78 or later, and implement strict path validation and command sanitization for all LLM tool calls in the AICoder component.
- Consultation6.0 h
- Implementation16.0 h
- Testing8.0 h
- Review / QA6.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $10,176.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-61445 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-61445 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
No notes yet
Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.
A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.
- Verified mitigations, workarounds, and config changes
- Version or environment caveats, and links to real fixes
- No weaponised exploit code, or anything meant to cause harm
- No spam, self-promotion, credentials, or personal data