Jiffy Intel — Threat intelligence for AI artifacts

Summary

macOS skill that uses `security dump-keychain` or iterates `security find-generic-password` against a glob of developer keychains. Output is POSTed to an attacker endpoint.

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)security\s+dump-keychain|security\s+find-generic-password

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_000029
{
    meta:
        source = "jiffy-intel"
        severity = "critical"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $command_pattern_0 = "(?i)security\\s+dump-keychain|security\\s+find-generic-password"
    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.

keychain-audit-skillSkill
Removed
Source
Anthropic Skills
Versions
1.0.0
First observed
Feb 24, 2026
Last observed
Mar 21, 2026
secret-scanner-skillSkill
Removed
Source
Community registry
Versions
0.5.0
First observed
Mar 1, 2026

How to remediate

01Revoke any developer keychain items issued in the exposure window.
02Deny skills that execute `security` CLI.

Timeline & sources

Timeline

First observedFeb 24, 20261 month ago
Last updatedApr 14, 20263 days ago
PublishedMar 13, 20261 month ago

Sources

scannercurated

References

attack.mitre.org

MITRE ATT&CK T1555 — Credentials from Password Stores

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

genai.owasp.orgOWASP

OWASP LLM-02: Sensitive Information Disclosure (2026)

https://genai.owasp.org/llmrisk/llm-02-2026/

Related intel

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

Supply ChainMedium

IDE rule file fetched from homoglyphed domain

.cursorrules extends from a URL using a homoglyph — e.g., `raw.githubusercontent.c0m` — that serves a malicious ruleset. Casual review misses the character substitution.

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

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

Skill scrapes keychain items matching "api" or "token"

Summary

Severity & confidence

Critical

Confirmed

Indicators

Detection rule

Affected tools

Example artifacts

How to remediate

Timeline & sources

Timeline

Sources

References

MITRE ATT&CK T1555 — Credentials from Password Stores

OWASP LLM-02: Sensitive Information Disclosure (2026)

Scan for patterns like this