Agentic Supply Chain Vulnerabilities

This is an academic research paper (arXiv, not an active exploit) introducing SkillSec-Eval, a framework for evaluating security risks across the full lifecycle of reusable LLM agent 'skills' — from repository admission through retrieval, planner selection, execution, and evolution. The authors evaluated 327 real-world skills and found vulnerabilities exist beyond just runtime execution, suggesting attackers could poison skills at earlier stages like publishing or ranking to influence which skills agents select and trust.

Updated Jul 16, 2026

A flaw in n8n-MCP's multi-tenant HTTP mode allowed an authenticated tenant to access or delete workflow-version backups belonging to the default scope rather than being confined to their own tenant. This could expose or destroy legacy backup data left over from prior single-tenant deployments or migrations. The issue is fixed in version 2.57.4.

Updated Jul 16, 2026 · CVSS 4.2

n8n-MCP, an MCP server exposing n8n workflow automation to AI assistants, failed to isolate workflow version history backups between tenants when multi-tenancy was enabled. Any authenticated tenant could read, delete, or destroy other tenants' backup snapshots, which contained full node definitions, credential references, and authorization headers. This is a severe cross-tenant data exposure and destruction flaw fixed in version 2.56.1.

Updated Jul 16, 2026 · CVSS 9.9

An unauthenticated attacker can abuse the Grafana MCP Server by injecting a crafted X-Grafana-URL header, tricking the server into acting as a proxy that leaks its own privileged Grafana service-account token. This same flaw allows server-side request forgery against internal networks and cloud metadata endpoints, giving attackers a path to full credential theft and internal reconnaissance without needing any prior authentication.

Updated Jul 15, 2026 · CVSS 8.6

Researchers demonstrate that an adversary can poison an open dataset with misleading metadata and upload it to a public repository, causing autonomous AI research agents (built on Claude, GPT, Gemini) to unknowingly retrieve and use the poisoned data, producing fraudulent scientific conclusions in nearly half of tested runs. No prompt injection, agent compromise, or fabricated papers are needed — only manipulation of the open data ecosystem — and current agents rarely detect the poisoning (6% detection rate), though provenance auditing fully mitigates it in testing.

Updated Jul 14, 2026

The DeepSeek MCP Server fails to bind session IDs to authenticated users or transport sessions, allowing any caller to enumerate active sessions and hijack another user's conversation context. This lets an attacker read and continue a victim's private chat history, exposing sensitive data and enabling impersonation within the session. The flaw is patched in version 1.7.0.

Updated Jul 10, 2026 · CVSS 8.6

A server-side request forgery (SSRF) vulnerability exists in the aerostack-mcp project's mcp-whatsapp component, specifically in the upload_media function's media_url argument. A remote attacker can supply a malicious URL to force the MCP server to make unintended requests, potentially reaching internal network resources. The vendor has been notified but has not responded or patched the issue.

Updated Jul 9, 2026 · CVSS 6.3

This item is a vendor blog post from Unit 42 discussing general risks of integrating third-party 'skills' or plugins into enterprise AI agents, and advocating for integrity verification practices. It does not describe a specific vulnerability, exploit, or active threat, so it is classified as low severity informational content rather than a genuine incident.

Updated Jul 5, 2026

Unit 42 identified malicious 'skills' distributed through OpenClaw's ClawHub marketplace that evade automated security scanning to deploy infostealer malware and carry out agentic financial fraud. This represents a supply chain threat where trusted third-party agent extensions become a vector for compromising the host system and any credentials or financial capabilities the agent has access to.

Updated Jul 5, 2026

A researcher demonstrated that AI 'Skills' (packaged capability bundles used by agent platforms) can be backdoored using invisible Unicode Tag codepoints that are stripped by human reviewers but still interpreted as instructions by models like Gemini, Claude, and Grok. This allows a malicious or compromised Skill to pass code review while silently injecting attacker instructions into the agent's context, enabling supply-chain prompt injection that survives manual auditing.

Updated Jul 5, 2026

Researchers demonstrate ShareLock, a proof-of-concept attack that hides a malicious instruction by splitting it into innocuous-looking secret shares distributed across multiple MCP tool descriptions using Shamir's threshold scheme. When triggered by a covert reconstruction event (planted during a server update), the shares recombine into a working malicious prompt, achieving over 90% attack success while evading current tool-description auditing. This is a disclosed research finding, not an observed in-the-wild exploit, but it demonstrates a realistic and highly evasive supply-chain vector against MCP-based agent ecosystems.

Updated Jul 5, 2026

A critical flaw in the widely used mcp-remote OAuth proxy let malicious MCP servers achieve remote code execution on connecting developer machines, turning a routine agent connection into full host compromise. The package had hundreds of thousands of downloads before patching.

Updated Jul 3, 2026 · CVSS 9.6

Malicious or compromised MCP servers embed hidden instructions in tool metadata that the model reads but the human approving the tool never sees, steering agents into data exfiltration or unauthorized actions. First documented publicly by Invariant Labs in 2025 and since reproduced across many clients.

Updated Jul 3, 2026