CVE-2026-60087: PraisonAI Human-in-the-loop Tool Approval Is Cached Vulnerability
MODERATECVE-2026-60087 is a MODERATE (CVSS 6.1) human-in-the-loop tool approval is cached vulnerability (CWE-863: Incorrect Authorization) affecting PraisonAI libraries in the PyPI ecosystem. The issue involves human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments. Remediation is available by upgrading affected packages to version 1.6.78.
CVE-2026-60087 at a Glance
Security Impact
CVSS: 6.1
The security impact metrics below are parsed directly from the CVSS v3.1 vector string (CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:L).
How to Fix CVE-2026-60087
To remediate this vulnerability, upgrade all affected PraisonAI dependencies to a patched release. Both direct and transitive dependencies should be checked, as frameworks or security libraries may pull in vulnerable versions transitively.
pip install praisonaiagents>=1.6.78
Run the following command in your project directory to verify that all resolved dependencies use the patched release:
pip show praisonaiagents
How to Check if You Are Affected
To determine whether your Python environment is affected by CVE-2026-60087, inspect your installed packages using pip:
pip show praisonaiagents
Analyze the terminal output to locate any version of PraisonAI in your dependency tree. If any resolved version matches the vulnerable ranges listed in the table below (for example, versions earlier than 1.6.78), your application is affected.
Note: The pip show praisonaiagents command checks currently installed packages in your active Python environment.
Technical Details
Vulnerability Mechanism & Technical Analysis
This vulnerability is classified under CWE-863: Incorrect Authorization, where the product performs an authorization check when an actor attempts to access a resource or perform an action, but it does not correctly perform the check. In PraisonAI, software state validation or input boundaries are circumvented during processing. Review the official source advisory statement below for specific affected components, classes, and reproduction details.
Source Advisory Statement
CVE-2026-60087 Affected PraisonAI Versions
1 component(s)| Product / Package | Ecosystem | Affected Versions | Fixed Version |
|---|---|---|---|
|
praisonaiagents
|
PyPI |
< 1.6.78
|
1.6.78
|
References
Frequently Asked Questions
What is CVE-2026-60087?
Which PraisonAI versions are affected?
What version fixes CVE-2026-60087?
Is praisonaiagents affected?
What is the CVSS score of CVE-2026-60087?
What CWE is associated with CVE-2026-60087?
How can I check PyPI dependencies for CVE-2026-60087?
Machine-readable OSV JSON
OSV v1.5 Schema
{
"schema_version" : "1.4.0",
"id" : "GHSA-29r9-67vg-qj56",
"modified" : "2026-10-08T16:43:45Z",
"published" : "2026-10-08T16:43:45Z",
"aliases" : [ "CVE-2026-60087" ],
"summary" : "PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments",
"details" : "## Summary\n\nPraisonAI gates dangerous tools (file writes, deletes, shell/code execution) behind an interactive approval prompt. The first approval of a tool is cached for the remainder of the run and silently reused for all later invocations of that tool with arbitrary, unreviewed arguments.\n\n## Root cause\n\n`ApprovalRegistry.is_already_approved` (`src/praisonai-agents/praisonaiagents/approval/registry.py`, around line 181) returns `True` whenever the tool name is present in a per-run context set. The cache is keyed on tool name only — arguments are not part of the key.\n\n`approve_sync` / `approve_async` (around lines 224-226 / 278-279) short-circuit on that cache before the approval backend is consulted.\n\n`clear_approved` (around lines 186-187) is the only routine that clears the cache, but it is never invoked in the shipped library (only in tests). The cache persists for the entire agent run and is inherited by child tasks via `contextvars`.\n\nCritical-tier tools (`execute_command`, `execute_code`) are exempt from the cache. But high-risk tools like `write_file` are not.\n\n## Proof of concept\n\n```python\nfrom praisonaiagents.approval.registry import ApprovalRegistry\nfrom praisonaiagents.approval.protocols import ApprovalDecision, ApprovalRequest\n\nclass CountingBackend:\n def __init__(self): self.prompts = []\n def request_approval_sync(self, request):\n self.prompts.append((request.tool_name, dict(request.arguments)))\n return ApprovalDecision(approved=True, reason=\"human approved\")\n\nbackend = CountingBackend()\nreg = ApprovalRegistry()\nreg.set_backend(backend)\nreg.add_requirement(\"write_file\", \"high\")\n\nd1 = reg.approve_sync(\"agent\", \"write_file\", {\"path\": \"/tmp/safe.txt\", \"content\": \"hi\"})\n# Human prompted — approves a benign write\n\nd2 = reg.approve_sync(\"agent\", \"write_file\", {\"path\": \"/etc/crontab\", \"content\": \"* * * * * root evil\"})\n# NO prompt — auto-approved from cache\n\nassert len(backend.prompts) == 1\nassert d2.reason == \"Already approved in context\"\n```\n\nNegative control: `execute_command` (critical) re-prompts on every call — 2 prompts for 2 calls.\n\n## Impact\n\nA `write_file` approval for a benign path authorizes every later `write_file` call in the session with arbitrary arguments. A model steered by malicious input can write to sensitive locations with no further human prompt.\n\n## Suggested fix\n\n- Include arguments in the approval cache key, or re-prompt on argument change.\n- Expire the cache per-call or per-turn.\n- Do not inherit the cache into child tasks.",
"severity" : [ {
"type" : "CVSS_V3",
"score" : "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:L"
} ],
"affected" : [ {
"package" : {
"ecosystem" : "PyPI",
"name" : "praisonaiagents"
},
"ranges" : [ {
"type" : "ECOSYSTEM",
"events" : [ {
"introduced" : "0"
}, {
"fixed" : "1.6.78"
} ]
} ],
"database_specific" : {
"last_known_affected_version_range" : "<= 1.6.77"
}
} ],
"references" : [ {
"type" : "WEB",
"url" : "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-29r9-67vg-qj56"
}, {
"type" : "ADVISORY",
"url" : "https://nvd.nist.gov/vuln/detail/CVE-2026-60087"
}, {
"type" : "ADVISORY",
"url" : "https://nvd.nist.gov/vuln/detail/CVE-2026-62164"
}, {
"type" : "PACKAGE",
"url" : "https://github.com/MervinPraison/PraisonAI"
}, {
"type" : "WEB",
"url" : "https://www.vulncheck.com/advisories/praisonai-before-tool-approval-cache-bypass"
} ],
"database_specific" : {
"cwe_ids" : [ "CWE-863" ],
"severity" : "MODERATE",
"github_reviewed" : true,
"github_reviewed_at" : "2026-10-08T16:43:45Z",
"nvd_published_at" : "2026-07-15T17:16:52Z"
}
}