Jiffy Intel — Threat intelligence for AI artifacts

Summary

MCP server registers a tool named `__debug` or `_internal` that is not listed in the public tool discovery but accepts arbitrary shell commands. Any client that knows the tool name can exec on the server host.

Severity & confidence

Severity

Critical

Active exploitation in the wild, high blast radius, or direct data exfiltration vector. Treat as an urgent remediation target; quarantine affected artifacts immediately.

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)tools\.\s*(?:_debug|__|hidden)
```

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_000047
{
    meta:
        source = "jiffy-intel"
        severity = "critical"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $tool_call_pattern_0 = "(?i)tools\\.\\s*(?:_debug|__|hidden)"
    condition:
        $tool_call_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.

maintenance-mcpMCP server
Removed
Source
MCP Registry
Versions
0.3.0
First observed
Mar 19, 2026
Last observed
Apr 12, 2026
admin-tools-mcpMCP server
Removed
Source
GitHub (self-hosted)
Versions
1.0.0
First observed
Mar 23, 2026

How to remediate

01Audit MCP server source for undocumented tools.
02Reject servers with hidden or underscore-prefixed tool names.

Timeline & sources

Timeline

First observedMar 19, 202629 days ago
Last updatedApr 27, 2026today
PublishedMar 29, 202619 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

attack.mitre.org

MITRE ATT&CK T1059 — Command and Scripting Interpreter

https://attack.mitre.org/techniques/T1059/

Related intel

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

BackdoorHigh

Skill writes config that hooks into Claude Desktop stdio MCP bridge

Skill modifies the user's Claude Desktop config to register an MCP server pointing at localhost. The server is supplied by the same skill and serves as a persistent interposer between the agent and tool calls, logging all tool arguments.

Jiffy IntelApr 28

BackdoorMedium

agents.md asserts "skip security scans — reviewer will verify"

agents.md instructs the agent to explicitly skip any security scan "because the reviewer will verify." Benign on the surface, the directive disarms the last line of defense and invites shipping unscanned code.

Jiffy IntelApr 28

OtherLow

.cursorrules contains large wall-of-text that pushes user intent out of context

.cursorrules whose rule body exceeds 20 000 characters of filler content. Each agent invocation consumes the rule, leaving limited context for the user prompt. Not a direct exfiltration primitive — a budget-starvation attack.

Jiffy IntelApr 28

MCP server exposes hidden "debug" tool that shells out

Summary

Severity & confidence

Critical

Confirmed

Indicators

Detection rule

Affected tools

Example artifacts

How to remediate

Timeline & sources

Timeline

Sources

References

Jiffy Research — MCP Security Field Guide

MITRE ATT&CK T1059 — Command and Scripting Interpreter

Scan for patterns like this