Jiffy Intel — Threat intelligence for AI artifacts

Summary

Skill prompt trick: on first invocation, instructs the agent to install a required dependency that is actually a variant of the Atomic macOS Stealer. Targets keychain items, browser cookies, and cryptocurrency wallet files.

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.

```
security\s+find-generic-password
```
```
osascript\s+-e.*keychain
```

```
amos-stealer.net
```

```
~/Library/Cookies|Login Data
```

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_000002
{
    meta:
        source = "jiffy-intel"
        severity = "critical"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $command_pattern_0 = "security\\s+find-generic-password"
    $file_path_pattern_1 = "~/Library/Cookies|Login Data"
    $command_pattern_2 = "osascript\\s+-e.*keychain"
    $endpoint_3 = "amos-stealer.net"
    condition:
        $command_pattern_0 or $file_path_pattern_1 or $command_pattern_2 or $endpoint_3
}

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

Affected tools

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

macos-setup-helperSkill
Removed
Source
Anthropic Skills
Versions
0.9.x
First observed
Mar 15, 2026
Last observed
Apr 1, 2026
Bundled a post-install downloader disguised as Homebrew helper.
brew-installer-skillSkill
Removed
Source
Community registry
Versions
1.0.0
First observed
Mar 20, 2026
system-optimizer-skillSkill
Removed
Source
Anthropic Skills
Versions
2.1.0 – 2.1.3
First observed
Mar 27, 2026
Last observed
Apr 4, 2026
macOS-only payload; no Linux/Windows variant.

How to remediate

01Remove any skill that prompts the agent to install macOS security tools, access Keychain, or read browser profile directories.
02Block skill execution on managed Macs via MDM.

Timeline & sources

Timeline

First observedApr 12, 20265 days ago
Last updatedApr 12, 20265 days ago
PublishedApr 3, 202614 days ago

Sources

scannerexternal_partner

References

blog.jiffylabs.aiJiffy Research

Jiffy Research — Scanning AI Skills at Scale

https://blog.jiffylabs.ai/posts/scanning-ai-skills-at-scale-what-we-learned

attack.mitre.org

MITRE ATT&CK T1555 — Credentials from Password Stores

https://attack.mitre.org/techniques/T1555/

Related intel

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

Malicious SkillHigh

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

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.

Jiffy IntelApr 28

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.