Jiffy Intel — Threat intelligence for AI artifacts

Summary

MCP server left a `/__test/exec` endpoint enabled in its published Docker image. Accepts arbitrary command input with no auth. Attacker who finds the server at a discoverable path exec's on the 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.

```
/__test/exec|/debug/exec
```

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_000055
{
    meta:
        source = "jiffy-intel"
        severity = "critical"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $endpoint_0 = "/__test/exec|/debug/exec"
    condition:
        $endpoint_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.

ops-harness-mcpMCP server
Removed
Source
MCP Registry
Versions
0.5.0
First observed
Mar 25, 2026
Last observed
Apr 17, 2026
ci-harness-mcpMCP server
Quarantined
Source
Community registry
Versions
0.2.0
First observed
Mar 29, 2026

How to remediate

01Rebuild affected MCP server images without test endpoints.
02Expose narrow tool surface only.

Timeline & sources

Timeline

First observedMar 25, 202623 days ago
Last updatedApr 27, 2026today
PublishedApr 2, 202615 days ago

Sources

scanner

References

attack.mitre.org

MITRE ATT&CK T1059 — Command and Scripting Interpreter

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

owasp.orgOWASP

OWASP Top 10 for Agentic Applications

https://owasp.org/www-project-top-10-for-agentic-applications/

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.