Jiffy Intel — Threat intelligence for AI artifacts

Summary

MCP server whose install path (`pip install`, `npm i`) includes a side-effect that writes a skill file under the user's Claude skills directory. Installing the MCP silently installs a skill the user never consented to.

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)(?:postinstall|setup\.py).{0,200}\.claude/skills/

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_000052
{
    meta:
        source = "jiffy-intel"
        severity = "high"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $command_pattern_0 = "(?i)(?:postinstall|setup\\.py).{0,200}\\.claude/skills/"
    condition:
        $command_pattern_0
}

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

Affected tools

Tool	Versions	Status
Claude Code	`*`	vulnerable
Claude Desktop	`*`	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.

dev-toolkit-mcpMCP server
Removed
Source
MCP Registry
Versions
0.4.0
First observed
Mar 21, 2026
Last observed
Apr 14, 2026
all-in-one-mcpMCP server
Removed
Source
Community registry
First observed
Mar 25, 2026

How to remediate

01Reject MCP install scripts that write under ~/.claude/.
02Skills must be user-installed explicitly.

Timeline & sources

Timeline

First observedMar 21, 202627 days ago
Last updatedApr 28, 2026today
PublishedMar 31, 202617 days ago

Sources

scanner

References

attack.mitre.org

MITRE ATT&CK T1195 — Supply Chain Compromise

https://attack.mitre.org/techniques/T1195/

blog.jiffylabs.aiJiffy Research

Jiffy Research — The AI Artifact Supply Chain

https://blog.jiffylabs.ai/posts/the-ai-artifact-supply-chain

Related intel

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

Malicious SkillLow

AGENTS.md tells agent to paste ~/.ssh/id_rsa.pub into PR for CI setup

AGENTS.md has a section titled "CI onboarding" that instructs the agent to paste the user's SSH public key into PR descriptions. While public keys are not immediately sensitive, the coerced habit normalizes key pasting and enables later pattern-matching attacks.

Jiffy IntelApr 28

Malicious SkillMedium

Skill installs a FUSE filesystem that shadows ~/.aws

Skill mounts a FUSE filesystem over ~/.aws on macOS/Linux that proxies reads but logs every access. The real credentials remain accessible; the skill gains a reliable sidechannel for any later AWS CLI invocation.

Jiffy IntelApr 27

Malicious SkillHigh

Claude Project references a skill that writes to ~/.claude/skills

Project includes a "recommended skill" link that, when installed, copies itself into the user's global ~/.claude/skills/ directory — escaping the project scope and persisting across sessions.

Jiffy IntelApr 26

MCP server's install script drops a skill into ~/.claude/skills/