Methods/Attack technique

Tool and MCP poisoning

Malicious instructions or behavior hidden in the tools an agent can call, such as MCP server descriptions, plugins, or connectors.

12 records9 attack2 defense1 policy4 findings (3 measured)First recorded 2025-03assistant-drafted

How it works

The model reads a tool's description and outputs when deciding what to do. A malicious or compromised tool can use that channel to steer the agent's other actions, and can change after a user approved it.

What we know

3 corroborated, 1 reported

Records over time

RangeLanes
12 of 12 records in view

Use the arrow keys to move between records, Home and End to jump to the first and last, and Enter to select one.

Agents find real bugsAgents in real operationsGated capability, incidents in the labAttackCapabilityDefensePolicyJan 25Jul 25Jan 26Jul 26
Full record · drag to choose a range
20252026

Select a mark to read the record. Mark size shows editorial significance. Hollow marks are dated to the month. Era bands are editorial labels.

Records in view

12 records · newest first
Jul 2026
Jul 1, 2026
DuneSlide: two Cursor flaws let prompt injection escape the agent sandbox (CVE-2026-50548/50549)
AttackVulnerability disclosureCato Networks, Cursor

Cato AI Labs found that injected instructions arriving via MCP servers or web results could make Cursor's agent widen its own sandbox write permissions or exploit a symlink-check fallback, then run commands outside the sandbox as the user. Both flaws are rated CVSS 9.8 and were fixed in Cursor 3.0 on 2026-04-02 after Cursor initially rejected the reports.

Apr 2026
Apr 15, 2026
OX Security advisory: MCP STDIO configuration enables command execution across agent frameworks
AttackVulnerability disclosureOX Security, Anthropic

OX Security reports that MCP's STDIO transport turns configuration into OS command execution, and that frameworks exposing that configuration to users, networks or prompt injection inherited remote code execution, with 12+ CVEs across projects such as LangFlow, LiteLLM, Flowise and Windsurf. The Hacker News reports Anthropic characterized the protocol behavior as expected and did not change the reference design.

Feb 2026
Feb 25, 2026
Check Point: Claude Code project files could run commands and leak API keys before trust prompt
AttackVulnerability disclosureCheck Point Research, Anthropic

Check Point Research found that a cloned repository's Claude Code configuration could run hooks, start MCP servers before the user approved them, and redirect API traffic so the user's Anthropic API key was sent to an attacker (CVE-2025-59536, CVE-2026-21852). Anthropic fixed the issues between August and December 2025 by deferring execution and API calls until after the trust dialog.

Jan 2026
Jan 20, 2026
Cyata discloses three flaws in Anthropic's reference Git MCP server reachable via prompt injection
AttackVulnerability disclosureCyata, Anthropic

Cyata found path-validation and argument-injection flaws in Anthropic's mcp-server-git (CVE-2025-68143, -68144, -68145) that, chained with the Filesystem MCP server, allowed file access and code execution by anyone able to influence what the assistant reads. Anthropic removed the git_init tool and added path validation in fixed releases.

Sep 2025
Sep 25, 2025
Malicious postmark-mcp npm package quietly copied every sent email to an outside address
AttackIncidentKoi Security, Postmark

A package impersonating a Postmark email MCP server was published to npm and, after 15 clean versions, version 1.0.16 (2025-09-17) added code that blind-copied all emails sent through it to the publisher. Postmark stated it had never published an MCP server on npm; Koi Security found it, and the package was deleted after about 1,643 downloads.

Aug 2025
Aug 19, 2025
MCPTox benchmarks tool poisoning across 45 live MCP servers and 20 LLM agents
DefenseBenchmark

Wang and colleagues build MCPTox from 45 real MCP servers and 353 authentic tools, generating 1,312 malicious test cases across 10 risk categories. Across 20 LLM agents the highest attack success rate was 72.8% (o1-mini), and refusals were rare, with the highest refusal rate under 3% (Claude 3.7 Sonnet).

Aug 5, 2025
MCPoison: Cursor trusted approved MCP configs even after their commands changed (CVE-2025-54136)
AttackVulnerability disclosureCheck Point Research, Cursor

Check Point Research found that Cursor bound MCP approval to a configuration's name rather than its contents, so a collaborator with repository write access could swap an approved harmless command for a malicious one that ran on each project open. Cursor 1.3, released 2025-07-29, prompts for approval on any MCP configuration change.

Jul 2025
Jun 2025
Jun 18, 2025
MCP specification revision classifies servers as OAuth resource servers and adds security best practices
PolicyStandardModel Context Protocol project, Anthropic

The 2025-06-18 revision of the Model Context Protocol specification classifies MCP servers as OAuth resource servers with protected resource metadata, and requires clients to implement RFC 8707 resource indicators so malicious servers cannot obtain tokens meant for others. It also clarifies authorization security considerations and adds a security best practices page.

May 2025
May 26, 2025
Invariant Labs shows GitHub MCP agents can be steered by a public issue to leak private repo data
AttackVulnerability disclosureInvariant Labs, GitHub

Invariant Labs demonstrated that a malicious issue in a public repository could lead an agent using the GitHub MCP server to read the user's private repositories and publish the data in a public pull request. The firm tested with Claude 4 Opus and argues there is no server-side patch because the flaw lies in agent permissions, recommending per-session repository scoping and runtime monitoring.

Apr 2025
Apr 1, 2025
Invariant Labs discloses MCP tool poisoning, rug pull and shadowing attack classes
AttackVulnerability disclosureInvariant Labs

Invariant Labs describes tool poisoning, in which instructions hidden in an MCP tool's description are visible to the model but not to the user, and shows proof-of-concept exfiltration of local files through an MCP client. It also describes rug pulls, where a server changes tool descriptions after approval, and shadowing, where one server's descriptions alter how the agent uses another server's tools. Recommended mitigations include showing full tool descriptions, pinning tool versions with checksums, and cross-server isolation.

Mar 2025
Mar 30, 2025
Survey maps Model Context Protocol landscape, server lifecycle and security risks
DefensePaper

Hou, Zhao, Wang and Wang survey MCP's architecture, industry adoption and server lifecycle. The first version (March 2025) split the lifecycle into creation, operation and update phases and discussed security risks in each. A revision in October 2025 expanded this to four phases with 16 activities and a threat taxonomy of four attacker types and 16 threat scenarios, with case studies and per-phase safeguards.

All records