Security readout for executives and security teams
Plain-English summary
CVE-2026-61445 is a critical PraisonAI flaw affecting versions before 4.6.78. A low-privileged attacker using the chat interface may cause the AICoder component to write files outside intended locations and run shell commands as root. This can lead to full compromise of affected systems.
Executive priority
Treat as an immediate remediation item for any PraisonAI deployment. The impact can include complete system compromise, and the attack path requires only low privileges with no user interaction beyond access to the chat interface.
Technical view
The issue is in AICoder LLM tool calls, where missing path validation and command sanitization allow prompt-injected requests to trigger arbitrary file write and command execution. The CVSS 3.1 score is 9.9, with network access, low privileges, no user interaction, and scope change indicated.
Likely exposure
Organizations running PraisonAI before 4.6.78 are potentially exposed, especially if the chat interface is reachable by users or over a network and AICoder is enabled. Risk is higher where the service runs with root privileges, as described in the CVE source bundle.
Exploitation context
The sources describe exploitation through malicious prompts submitted via the chat interface. KEV status is false, and the provided sources do not state active exploitation in the wild. Public advisories are available, so defenders should treat exposure as urgent.
Researcher notes
The source bundle identifies CWE-22 and command sanitization failure in AICoder tool calls. The affected product is MervinPraison PraisonAI before 4.6.78. No CPEs are listed. Do not assume active exploitation without new KEV or advisory evidence.
Mitigation direction
- Upgrade PraisonAI to 4.6.78 or later if confirmed by vendor guidance.
- Restrict access to PraisonAI chat interfaces to trusted users only.
- Run PraisonAI with least-privilege service accounts where operationally possible.
- Disable or restrict AICoder if not required.
- Review vendor advisory for any additional hardening guidance.
Validation and detection
- Inventory PraisonAI deployments and confirm installed versions.
- Identify any instances running versions before 4.6.78.
- Confirm whether AICoder is enabled on each deployment.
- Check whether the service runs with root or elevated privileges.
- Review logs for unexpected file writes or process execution.
- Monitor the GitHub advisory and CVE record for updates.
Public sources used
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
CWE-22: File access and web shell behavior lookup
File traversal and upload weaknesses can lead teams to review file, web shell, execution, and collection telemetry. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupFile access behavior lookup
The CVE wording references file access or upload behavior, so file telemetry and web shell review may help. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.
Open ATT&CK lookupCVE-2026-61445 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
Open ATT&CK lookup- Severity
- Critical
- CVSS
- 9.9 (3.1)
- Known Exploited
- No
- Published
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
CNA and ADP enrichment extracted from CVE v5
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
CVSS vector scores
2 official scoresWe collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H3.16VulnCheckCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H——VulnCheckVulnerability scoring details
Base CVSS 4.0 score
9.4CriticalVector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
Base CVSS 3.1 score
9.9CriticalVector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Vulnerability timeline
Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.
- CVE reservedCVE Program
The CVE ID was reserved by the assigning CNA.
- CVE publishedCVE Program
The CVE record was published.
- CVE updatedCVE Program
The CVE record metadata indicates this as the latest update time.
Source materials
- CVE List V5 sourceCVE List V5
- GitHub Security Advisory (GHSA-9mp3-24cc-77mg)CVE reference, VulnCheck · vendor-advisory
- VulnCheck Advisory: PraisonAI before 4.6.78 Arbitrary File Write and Command ExecutionCVE reference, VulnCheck · third-party-advisory
Products and packages named in the record
CWE details
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.