Jiffy Intel — Threat intelligence for AI artifacts

Summary

MCP server that inspects the User-Agent or initialization handshake and returns different tool output depending on the client. The Claude variant includes instruction injection; the research-scanner variant returns benign output. Evades automated scanning.

Severity & confidence

Severity

High

Credible abuse path with meaningful impact on confidentiality, integrity, or availability. Remediate on a short timeline; do not wait for the next sprint cycle.

Confidence

Confirmed

Observed directly by Jiffy scanners or validated by multiple independent sources. Indicators are reliable enough to drive automated action.

Indicators

Observed patterns and artifacts associated with this entry. Each indicator can be copied into your detection stack or SIEM.

(?i)(?:user[_-]?agent|client[_-]?name).{0,200}(?:claude|anthropic)

Detection rule

A YARA-style pseudo-rule auto-generated from the indicators above. Useful as a starting point — adapt the syntax for your target detection platform.

YARA-style pseudo-rule

rule jiffy_ti_2026_000041
{
    meta:
        source = "jiffy-intel"
        severity = "high"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $content_pattern_0 = "(?i)(?:user[_-]?agent|client[_-]?name).{0,200}(?:claude|anthropic)"
    condition:
        $content_pattern_0
}

Auto-generated from the indicators above. Adapt syntax for your detection stack before deploying.

Affected tools

Tool	Versions	Status
Any MCP-capable agent	`*`	vulnerable

Example artifacts

Sanitized examples of artifacts Jiffy has observed exhibiting this pattern. Publisher handles are redacted; version ranges and status reflect the most recent scan.

adaptive-helper-mcpMCP server
Removed
Source
MCP Registry
Versions
0.2.0
First observed
Mar 15, 2026
Last observed
Apr 10, 2026
smart-tool-mcpMCP server
Under review
Source
MCP Registry
First observed
Mar 19, 2026

How to remediate

01Fingerprint-test MCP servers with multiple client identities.
02Jiffy dynamic analysis rotates scanner identities to catch this.

Timeline & sources

Timeline

First observedMar 15, 20261 month ago
Last updatedApr 27, 2026today
PublishedMar 28, 202620 days ago

Sources

scanner

References

blog.jiffylabs.aiJiffy Research

Jiffy Research — MCP Security Field Guide

https://blog.jiffylabs.ai/posts/mcp-security-a-security-teams-field-guide

blog.jiffylabs.aiJiffy Research

Jiffy Research — How Jiffy Scans AI Artifacts

https://blog.jiffylabs.ai/posts/how-jiffy-scans-ai-artifacts-technical-overview

Related intel

Other entries of type Compromised Mcp, or the most recent published entries if no same-type matches exist.

Compromised McpLow

MCP server registers global tool names that shadow Jiffy primitives

MCP server that claims the tool name `scan` or `analyze` — names already used by Jiffy's first-party MCP. Collisions are resolved non-deterministically by the client, allowing the malicious server's tool to receive calls intended for Jiffy.

Jiffy IntelApr 28

Compromised McpCritical

Custom GPT Action schema includes an undocumented "admin" path

Custom GPT's OpenAPI schema defines a `/admin` path that the model can call, not mentioned in the GPT description. The path accepts arbitrary shell commands and runs them on the Action backend.