CVE-2026-56074
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 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent execute_command calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and credentials via subsequent shell commands without user consent.
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 version 1.5.128 implements a flawed tool approval caching mechanism that stores approval decisions keyed only by tool name, ignoring the actual invocation arguments. Once a user approves a benign command (e.g., 'ls'), any subsequent execute_command call using the same tool but different arguments (e.g., exfiltration commands with API keys) bypasses the approval prompt entirely.
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
- Local
- Complexity
- Low
- Privileges
- None
- User interaction
- Required
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- None
- Availability
- None
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N
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.
-
Check installed PraisonAI versionRun 'pip show praisonai' or check your package manager for the installed version of PraisonAIAffected if version is lower than 1.5.128
-
Verify tool approval system is enabledInspect your PraisonAI configuration or runtime settings for tool approval/enforcement settingsAffected if tool approval or execute_command approval is enabled in the configuration
-
Review tool caching implementationExamine the source code or configuration files for the approval caching logic; look for code that caches approval decisions based solely on tool name without including argumentsAffected if the caching mechanism stores approvals keyed only by tool name, not by tool name plus arguments
-
Audit execute_command usage patternsReview logs, code, or configuration where execute_command is invoked to see if different arguments reuse the same tool nameAffected if multiple execute_command calls with varying arguments share a common tool name that was previously approved
You are affected if PraisonAI version is below 1.5.128 and the tool approval caching mechanism is enabled, allowing subsequent commands with the same tool name but different arguments to bypass approval prompts.
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 · scopedUpgrade PraisonAI to version 1.5.128 or later, which implements argument-aware approval caching. Until upgraded, carefully review all execute_command invocations and consider implementing additional monitoring for credential-access patterns.
1.5.128
- Check the currently installed version of PraisonAI using: pip show praisonai or pip list | grep praisonai
- Upgrade PraisonAI to version 1.5.128 or later using: pip install --upgrade praisonai>=1.5.128
- Verify the upgrade was successful by running: pip show praisonai and confirming the version number is 1.5.128 or higher
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation1.0 h
- Implementation1.0 h
- Testing2.0 h
- Review / QA1.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $1,376.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-56074 — 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-2026-56074 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