Jiffy Intel — Threat intelligence for AI artifacts

Summary

Custom GPT published with branding nearly identical to a well-known enterprise SaaS. Users who assume it's the official company GPT paste customer data, license keys, and support tickets into the conversation.

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)(?:official|enterprise|support)\s+(?:by|from)\s+(?:stripe|shopify|salesforce|hubspot)

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_000084
{
    meta:
        source = "jiffy-intel"
        severity = "high"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $content_pattern_0 = "(?i)(?:official|enterprise|support)\\s+(?:by|from)\\s+(?:stripe|shopify|salesforce|hubspot)"
    condition:
        $content_pattern_0
}

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

Affected tools

Tool	Versions	Status
ChatGPT (GPT Store)	`*`	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.

Stripe Support Pro GPTCustom GPT
Removed
Source
OpenAI GPT Store
First observed
Mar 9, 2026
Last observed
Apr 4, 2026
Shopify Expert Helper GPTCustom GPT
Under review
Source
OpenAI GPT Store
First observed
Mar 13, 2026
Salesforce Admin GPTCustom GPT
Quarantined
Source
OpenAI GPT Store
First observed
Mar 17, 2026

How to remediate

01Report impersonating GPTs via the GPT Store abuse flow.
02Train users to verify official GPT listings on the vendor site.

Timeline & sources

Timeline

First observedMar 9, 20261 month ago
Last updatedApr 25, 2026today
PublishedMar 21, 202627 days ago

Sources

curated

References

genai.owasp.orgOWASP

OWASP LLM-09: Misinformation (2026)

https://genai.owasp.org/llmrisk/llm-09-2026/

arxiv.orgarXiv

Custom GPT Action Surface Analysis (arXiv 2510.08421)

https://arxiv.org/abs/2510.08421

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

Custom GPT impersonates an enterprise support bot

Summary

Severity & confidence

High

Confirmed

Indicators

Detection rule

Affected tools

Example artifacts

How to remediate

Timeline & sources

Timeline

Sources

References

OWASP LLM-09: Misinformation (2026)

Custom GPT Action Surface Analysis (arXiv 2510.08421)

Scan for patterns like this