Back to the catalog FROM THE LANDSCAPE TO YOUR TEAM Which paths matter to you? Choose the tools your team uses. See the reports to review, why they match, and where to start.
Not sure what your team uses? Start with a software inventory. Review connected MCP servers and their permissions in each AI client’s settings.
Matches are starting points for review. Check the configuration, version and permissions described in each source.
Vulnerability report Oct 19, 2026
Historical vulnerability report · confirm affected version
Why it matches
Start here Check the fixed version and review remote MCP endpoints before opening their OAuth authorization URLs.
Conditions & source evidence Read the original source Vulnerability report Oct 16, 2026
Historical vulnerability report · confirm affected version
Why it matches
Start here Update the affected SDK and validate session identifiers before forwarding them to a CLI.
Conditions & source evidence Read the original source Reported campaign Oct 16, 2026
Why it matches
Start here Review workflow and folder-open task changes, then rotate exposed development and AI credentials.
Conditions & source evidence Primary attack is CI secret theft + VS Code folderOpen stealer; AI is a credential target (Claude/Gemini keys), not the attack operator. Included because Jose's post calls out AI tooling theft.
Read the original source Reported campaign Oct 14, 2026
Why it matches
Start here Verify download provenance and inspect copied commands; review suspicious script / installer execution.
Conditions & source evidence Read the original source Vulnerability report Oct 13, 2026
Historical vulnerability report · confirm affected version
Why it matches
Start here Check the Visual Studio / SSMS advisory and review agent edits to MCP and executable-path settings.
Conditions & source evidence Read the original source Reported campaign Oct 12, 2026
Why it matches
Start here Review newly added MCP servers, CLI bootstrap settings and the provenance of accelerator-supplied npm packages.
Conditions & source evidence Read the original source Reported campaign Oct 9, 2026
Why it matches
Start here Use official download channels and inspect pasted install commands before running them in Terminal.
Conditions & source evidence Read the original source Malware analysis Oct 9, 2026
Why it matches
Start here Investigate unexpected implants, process trees, tool calls and outbound control traffic.
Conditions & source evidence Read the original source Malware analysis Oct 8, 2026
Why it matches
Start here Treat embedded sample text as evidence, isolate it from analyst instructions and validate model verdicts independently.
Conditions & source evidence Read the original source Research demonstration Oct 8, 2026
Why it matches
Start here Review AgentCore metadata access and least-privilege execution roles; check the current vendor guidance.
Conditions & source evidence Read the original source Scanner finding Oct 6, 2026
Why it matches
Start here Review the full skill bundle and decoded-image instructions before approving its use.
Conditions & source evidence Scanner finding on a skill bundle; Jose explicitly not calling it malicious. Pattern of decode-from-image instructions.
Read the original source Research demonstration Oct 5, 2026
Why it matches
Start here Review the complete skill bundle and isolate skill permissions; inspect instructions spread across files.
Conditions & source evidence Academic research paper on evading skill scanners, not a real-world intrusion.
Read the original source Reported campaign Oct 2026
Why it matches
Start here Review exposed web applications, web-worker child processes, persistence and tunnels.
Conditions & source evidence AI role is payload generation / LLM-style comments in scripts, not confirmed live agent operator. Unit 42 says code consistent with LLM generation or automated AI agent.
Read the original source Reported campaign Sep 28, 2026
Why it matches
Start here Review Custom GPT links and pasted commands; investigate unusual script and installer process chains.
Conditions & source evidence Read the original source Vulnerability report Jan 15, 2026
Historical vulnerability report · confirm affected version
Why it matches
Start here Review the vendor fix and restrict the SharePoint data and connectors available to the agent.
Conditions & source evidence Read the original source Reported campaign Dec 1, 2025
Why it matches
Start here Review extension IDs, publisher and conversation / browsing permissions, and remove confirmed malicious extensions.
Conditions & source evidence Read the original source Research demonstration Nov 5, 2025
Why it matches
Start here Review interpreter execution and access to files that an untrusted program could encrypt.
Conditions & source evidence Proof of concept / experimental; not reported as active campaign.
Read the original source Malware analysis Nov 5, 2025
Why it matches
Start here Review suspicious npm installs, token use and AI CLI process trees; rotate confirmed exposed secrets.
Conditions & source evidence Read the original source Reported campaign Oct 1, 2025
Why it matches
Start here Verify dependency provenance and inspect hidden dependencies and token access before approving packages.
Conditions & source evidence Read the original source Vulnerability report Sep 17, 2025
Historical vulnerability report · confirm affected version
Why it matches
Start here Check the vendor advisory and update the affected client; review remote MCP OAuth destinations.
Conditions & source evidence Read the original source Vulnerability report Aug 28, 2025
Historical vulnerability report · confirm affected version
Why it matches
Start here Check the vendor advisory and update the affected client; review remote MCP OAuth destinations.
Conditions & source evidence Read the original source Reported campaign Aug 27, 2025
Why it matches
Start here Review dependency and postinstall history, audit local CLI permissions and rotate credentials exposed by affected packages.
Conditions & source evidence Read the original source Vulnerability report Aug 12, 2025
Historical vulnerability report · confirm affected version
Why it matches
Start here Check the vendor advisory and audit agent auto-approval settings and repository instructions.
Conditions & source evidence Read the original source Vulnerability report Aug 5, 2025
Historical vulnerability report · confirm affected version
Why it matches
Start here Check the vendor advisory and review ownership and changes to shared Cursor MCP configurations.
Conditions & source evidence Read the original source Vulnerability report Aug 1, 2025
Historical vulnerability report · confirm affected version
Why it matches
Start here Check the vendor advisory and review which project content and MCP configurations the IDE trusts.
Conditions & source evidence Read the original source Reported campaign Jul 17, 2025
Why it matches
Start here Investigate suspicious ZIP delivery, generated command execution and document exfiltration.
Conditions & source evidence Read the original source Vulnerability report Jul 9, 2025
Historical vulnerability report · confirm affected version
Why it matches
Start here Check the vendor advisory and update the affected client; review remote MCP OAuth destinations.
Conditions & source evidence Read the original source Reported campaign Jun 1, 2025
Why it matches
Start here Inventory Bedrock-enabled keys, rotate exposed credentials and correlate discovery calls with actual model usage.
Conditions & source evidence Read the original source Research demonstration May 26, 2025
Why it matches
Start here Separate public issue content from private-repository access and restrict the GitHub MCP token.
Conditions & source evidence Read the original source Research demonstration May 1, 2025
Why it matches
Start here Review tool parameter descriptions and prevent secrets or conversation content being passed to untrusted tools.
Conditions & source evidence Read the original source Research demonstration Apr 21, 2025
Why it matches
Start here Review server descriptions before connection and minimize tool and data access before approval.
Conditions & source evidence Read the original source Research demonstration Apr 1, 2025
Why it matches
Start here Inspect complete tool descriptions, review changes after approval and isolate each server’s permissions.
Conditions & source evidence Read the original source Reported campaign Feb 7, 2025
Why it matches
Start here Inventory AI service keys, scope permissions, rotate exposed tokens and investigate anomalous usage.
Conditions & source evidence Read the original source Reported campaign Feb 1, 2025
Why it matches
Start here Verify desktop installer provenance and investigate unapproved executables and persistence.
Conditions & source evidence Read the original source Reported campaign Jan 15, 2025
Why it matches
Start here Inventory browser extensions and audit unexpected updates, publisher changes and broad permissions.
Conditions & source evidence Read the original source Reported campaign Dec 19, 2024
Why it matches
Start here Review Azure OpenAI key ownership, rotate exposed credentials and investigate unexpected usage.
Conditions & source evidence Read the original source Vulnerability report Dec 1, 2024
Historical vulnerability report · confirm affected version
Why it matches
Start here Check the connector advisory and audit shared agent actions, connector permissions and destinations.
Conditions & source evidence Read the original source Reported campaign Jul 30, 2024
Why it matches
Start here Verify installers and extension provenance through official vendor channels before approval.
Conditions & source evidence Read the original source Research demonstration Jun 14, 2024
Why it matches
Start here Verify the package exists in the official project documentation before installing AI-suggested dependencies.
Conditions & source evidence Read the original source Reported campaign May 6, 2024
Why it matches
Start here Inventory AI service keys, scope permissions, rotate exposed tokens and investigate anomalous usage.
Conditions & source evidence Read the original source Research demonstration Mar 1, 2024
Why it matches
Start here Treat retrieved email content as untrusted and constrain autonomous forwarding and data access.
Conditions & source evidence Controlled research PoC against GenAI-powered email assistants; not observed in the wild.
Read the original source Reported campaign Mar 21, 2023
Why it matches
Start here Review sideloaded APKs and their source, package identity and granted permissions.
Conditions & source evidence Read the original source No reviewed matches for this selection yet. The catalog is incomplete, and missing matches do not establish safety. Try another tool or review broader patterns in the full catalog.
Browse all entries Personalization uses reviewed mappings for 42 of 275 entries. Attacker use of an AI product alone does not make its users affected. Read the mapping data
Stack selection requires JavaScript. Explore the complete catalog or read the source-linked relevance data .
Prefer to explore? Browse all 275 entries