High Injection

CVE-2026-57142 — PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml

PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.61, PraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allow_dangerous_tools=True. That policy only checks tools declared in TEMPLATE.yaml requires.tools. For steps-based recipes, the actual execution path loads workflow.yaml with YAMLWorkflowParser. That parser resolves agent-level tools: declarations and preserves top-level approve:. Workflow.start() then installs those YAML-approved tools into the approval context. As a result, an untrusted recipe can omit execute_command from TEMPLATE.yaml requires.tools, declare it in workflow.yaml agents.*.tools, and add top-level approve: [execute_command]. The caller did not set allow_dangerous_tools=True, but the recipe policy allows the recipe and the workflow approval path self-approves the critical shell tool. This issue has been patched in version 4.6.61.

Published Oct 23, 2026 · Updated Oct 29, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP, GitHub Security Advisories · CNA: GitHub_M

Low

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.

How the score was calculated

EPSS 0.1% (30-day exploitation probability)+1
Technical severity (high)+6
CISA SSVC: exploitation "poc"+5

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation

Not confirmed

Not in CISA KEV — an absence of record, not proof it is unexploited.

EPSS FIRST

0.15%

ahead of 4% of scored CVEs · Oct 29, 2026

Affects

MervinPraison

PraisonAI and 1 more

CVSS base

7.8

High · 3 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation

Proof of concept

none · proof-of-concept · active

Automatable

can an attacker script the kill-chain steps

Technical impact

Total

partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

Pip Praisonai: fixed in version 4.6.61 — github.com (GitHub Security Advisories)

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

Identify exposed assets running the affected vendor/product/version combinations (MervinPraison PraisonAI, Pip Praisonai).
Apply the fixed version or the patch documented under Remediation.
Exploitation requires user interaction: tighten email/web filtering and warn affected users.
Search available logs for exploit probes matching the vulnerability class (injection), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

Vendor	Product	Versions	Status	Source
MervinPraison	PraisonAI	version >= 4.5.87, < 4.6.61	Vulnerable	CVE Program (cve.org) e CISA ADP
Pip	Praisonai	≥ 4.5.87 and < 4.6.61	Vulnerable	GitHub Security Advisories

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector

Local

Attack complexity

Low

Privileges required

None

User interaction

Required

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

Score	Version	Severity	Expl.	Impact	Scored by
7.8	CVSS 3.1	High	1.8	5.9	security-advisories@github.com via NIST National Vulnerability Database
7.8	CVSS 3.1	High	—	—	GitHub, Inc. via GitHub Security Advisories
7.8	CVSS 3.1	High	—	—	GitHub_M via CVE Program (cve.org) e CISA ADP

CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H (score shown at the top: security-advisories@github.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-78 · OS Command Injection

Other CVEs with this weakness →

EPSS over time FIRST

Oct 24, 2026 → Oct 29, 2026 · 6 reading(s) · max 0.20%

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

Local/physical vector: focus on endpoint telemetry (EDR) from affected hosts.
Look for parameters with command/query metacharacters and unexpected child processes of the service.

endpoint telemetry (EDR)application logs

Timeline

What happened to this CVE, newest first.

2026
SSVC assessment updated
Oct 29, 2026 · CVE Program (cve.org) e CISA ADP
Fix documented
Oct 23, 2026 · GitHub Security Advisories
Affected products added · pip/praisonai
Oct 23, 2026 · GitHub Security Advisories
Affected products added · mervinpraison/praisonai
Oct 23, 2026 · CVE Program (cve.org) e CISA ADP
Record published
Oct 23, 2026
CVSS changed · 7.8
Oct 23, 2026 · NIST National Vulnerability Database
Source status changed · → Deferred
Oct 23, 2026 · NIST National Vulnerability Database
Record created in this database
Oct 23, 2026 · Alertas do Telegram
CVE published
Oct 23, 2026 · GitHub_M

Source activity

Repeated readings are counted rather than listed.

2× References added · Oct 23, 2026 – Oct 23, 2026
1× Official description updated · Oct 23, 2026 – Oct 23, 2026

References

2 on the record

github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7qw2-w5rc-37x2
x_refsource_CONFIRM, NIST National Vulnerability Database
github.com/advisories/GHSA-7qw2-w5rc-37x2
GitHub Security Advisories

Elsewhere on this site

MervinPraison
every CVE for this vendor

Injection
same class

CWE-78
other pages naming this weakness

Related CVEs (same products)

High CVE-2026-57146 PraisonAI A2U incomplete authentication fix leaves current serve command unauthenticated by default 6d
High CVE-2026-57144 PraisonAI SandlockSandbox falls back to unrestricted subprocess execution when Landlock is unavailable 6d
High CVE-2026-57121 PraisonAI: Missing ownership check on DELETE endpoints allows members to delete others' content in Platform API 6d
High CVE-2026-57114 PraisonAI: Jobs webhook SSRF protection bypass via DNS rebinding 6d
High CVE-2026-57117 PraisonAI: Compute-bridged file tools allow shell command injection 6d
High CVE-2026-57113 PraisonAI GitHub template cache path traversal allows outside-cache file write and directory deletion 6d

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-57142 is "PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml", rated High. It affects PraisonAI (MervinPraison); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 7.8 describes technical severity. EPSS 0.15% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.