CVE-2026-56075
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 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approval_mode to auto, overriding administrator configuration from PRAISON_APPROVAL_MODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary shell commands via subprocess.run with shell=True, bypassing the manual approval gate and insufficient command sanitization blocklists.
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 4.5.128 has an arbitrary shell command execution vulnerability where UI modules hardcode approval_mode to 'auto', overriding the PRAISON_APPROVAL_MODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary shell commands via subprocess.run with shell=True, bypassing both the manual approval gate and blocklist-based sanitization.
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
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/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.
-
Identify installed PraisonAI versionRun 'pip show praisonai' or check the package version in your Python environment to determine if the version is before 4.5.128Affected if The installed version is earlier than 4.5.128
-
Locate UI module filesSearch the PraisonAI installation directory for files that contain UI-related code, such as files named with 'ui', 'interface', or similar patterns, or examine the main application entry pointsAffected if UI module files exist in the installation
-
Check for hardcoded approval_mode in UI modulesWithin UI module files, search for patterns like 'approval_mode' or 'PRAISON_APPROVAL_MODE' and verify if the value is explicitly set to 'auto' (for example: approval_mode = 'auto' or similar assignments)Affected if The UI module hardcodes approval_mode to 'auto', overriding the environment variable setting
-
Verify subprocess.run usageSearch the codebase for subprocess.run calls and inspect whether shell=True is used in the command execution logic accessible through the LLM agent interfaceAffected if subprocess.run with shell=True is present in the agent command execution path accessible to authenticated users
-
Test environment variable override behaviorSet PRAISON_APPROVAL_MODE to a non-auto value (such as 'manual') in the environment and verify through logs or code inspection whether the UI respects this setting or still operates in 'auto' modeAffected if Setting PRAISON_APPROVAL_MODE to 'manual' does not prevent command execution, indicating the variable is being overridden
The environment is affected if PraisonAI version is before 4.5.128 AND UI modules hardcode approval_mode to 'auto', causing the PRAISON_APPROVAL_MODE environment variable to be ignored and allowing authenticated users to bypass approval controls via subprocess.run with shell=True.
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.
dbcve · scopedRemove hardcoded approval_mode in UI modules to respect the PRAISON_APPROVAL_MODE environment variable, and replace blocklist-based command sanitization with allowlist-based filtering to prevent command injection.
4.5.128 or later
- Check current installed version: pip show praisonai or pip list | grep praisonai
- Upgrade to version 4.5.128 or later: pip install --upgrade praisonai>=4.5.128
- Verify the upgrade was successful: pip show praisonai
- Confirm the PRAISON_APPROVAL_MODE environment variable is now properly respected by the application
- Restart any running PraisonAI services to ensure the new version is fully loaded
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation3.0 h
- Implementation6.0 h
- Testing5.0 h
- Review / QA3.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $4,752.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-56075 — 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-2026-56075 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