CVE•Published 2025-06-11•1 article on news•6 live references•NVD data
CVE-2025-32711
Vulnerability data via CVEDB (Shodan)
CVSS v3.1
9.3
CRITICAL
EPSS percentile
91
Exploit Prediction Scoring System · top 9% of all CVEs
Description
Ai command injection in M365 Copilot allows an unauthorized attacker to disclose information over a network.
Timeline
Published 2025-06-11
External references
Search for exposed instances
Shodan + Censys queries derived from NVD's CPE data. The vuln tag catches assets Shodan has explicitly linked to this CVE; the product / banner fingerprints find exposed instances even when the vuln tag was never applied (which is common).
Shodan · vuln tag0 hosts
vuln:CVE-2025-32711Hosts Shodan has explicitly fingerprinted as vulnerable.
Shodan · product
product:"Microsoft 365 Copilot"All exposed Microsoft 365 Copilot instances — cross-reference with the CVE's affected-version range.
Shodan · banner/body mention
http.html:"365 Copilot"HTTP body or banner mentions "365 Copilot" — catches deploys Shodan didn't identify as a product.
More intel sources (5)
Shodan report
vuln:CVE-2025-32711Country / ASN / product breakdown for the vuln query.
Censys
vulnerabilities.cve_id: CVE-2025-32711Censys host search filtered to this CVE id.
grep.app
CVE-2025-32711Public source-code mentions — fast PoC discovery.
GitHub code
CVE-2025-32711GitHub code search for direct mentions.
Google dork
"CVE-2025-32711" exploit -site:nvd.nist.govWrite-ups and news, NVD excluded.
Known PoCs on GitHub (8)
CVE-2025-327118 repos
TalEliyahu/Awesome-AI-Securityunknown
Curated resources, research, and tools for securing AI systems
ZeroLeaks/zeroleaksTypeScript
AI Security Scanner - Test your AI systems for prompt injection and extraction vulnerabilities
requie/LLMSecurityGuideunknown
A comprehensive reference for securing Large Language Models (LLMs). Covers OWASP GenAI Top-10 risks, prompt injection, adversarial attacks, real-world incidents, and practical def…
ucsb-mlsec/Awesome-Agent-Securityunknown
bridge-mind/BridgeWardShell
Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, refusal templates, and a read-only injectio…
jeremylongshore/claude-code-slack-channelTypeScript
Slack-native governance substrate for Claude Code and peer agents: every tool call passes a tiered policy engine and lands in a hash-chained, Ed25519-signed audit journal you can v…
SecureNexusLab/llm-prompt-injection-security-handbookunknown
A comprehensive technical research report on LLM Prompt Injection threats, covering direct/indirect injection, jailbreaking, adversarial suffixes, and defense-in-depth architecture…
quantifylabs/aegis-memoryPython
Secure context engineering for AI agents. Content security · integrity verification · trust hierarchy · ACE patterns. Self-hosted, Apache 2.0.