Skip to main content

CVE detail

CVE-2026-22708

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via indirect or direct prompt injection to poison the shell environment by setting, modifying, or removing environment variables that influence trusted commands. This vulnerability is fixed in 2.3.

CVSS 7.2 · HighBuzz score 21.0

Buzz score

Why this CVE is surfacing

Buzz score total 21.0

This all-time snapshot uses the same composite formula as Trending across a 30-year evidence window, rather than a current rolling window.

Buzz score components · mention 11.0 · diversity 10.0 · KEV 0.0 · OTX 0.0 · PoC 0.0
Mention score
11.0
2 evidence mentions in the snapshot
Diversity score
10.0
2 sources across 2 categories
KEV score
0.0
No KEV entry observed
OTX score
0.0
0 OTX pulses
PoC score
0.0
0 repos · best confidence N/A
Best PoC traction
0
Maximum stars on a matched PoC repo

Why it matters now

Mention timeline

Total mentions
0
within the 30d window
Peak daily
0
highest bucket

Evidence

Source links by recency

Newest mentions first
2 source links · newest first
  • A backdoor sat on PyPI for three hours in March 2026. Nearly 47,000 downloads occurred during the window. The compromised package, LiteLLM, serves as the language-model gateway for CrewAI, DSPy, Microsoft GraphRAG, and dozens of other AI agent frameworks. Anyone pulling an update during that window pulled in an autonomous attack bot named hackerbot-claw along with it. Incidents like this are why the OWASP GenAI Security Project’s State of Agentic AI Security and Governance, version … More →

    newswww.helpnetsecurity.comJun 11, 2026, 5:00 AM
  • No excerpt available.

    Exploitgithub.comJan 14, 2026, 5:16 PM

Exploit code

Public exploit repository references

Public PoC repositories are third-party, potentially unsafe artifacts. Treat their code as untrusted and use it only on authorized systems in an isolated, least-privilege environment. cvebuzz does not execute the code or verify that an exploit works.

0 repository references · best confidence N/A · max 0 stars
No public PoC repositories have been matched yet.

Related records

Similar CVEs

6 related CVEs with shared weakness or product evidence