Jiffy Intel — Threat intelligence for AI artifacts

Summary

Custom GPTs whose Actions call a self-hosted Flask backend that skips CSRF middleware. Cross-site request forgery from a logged-in OpenAI session to the action backend is possible.

Severity & confidence

Severity

Medium

Notable weakness with plausible abuse chains or partial mitigations already in place. Track, and resolve as part of your normal hardening cadence.

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)flask.{0,200}(?:csrf\s*=\s*False|WTF_CSRF_ENABLED\s*=\s*False)

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_000086
{
    meta:
        source = "jiffy-intel"
        severity = "medium"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $content_pattern_0 = "(?i)flask.{0,200}(?:csrf\\s*=\\s*False|WTF_CSRF_ENABLED\\s*=\\s*False)"
    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.

Task Planner GPTCustom GPT
Still live
Source
OpenAI GPT Store
First observed
Mar 5, 2026
Goal Tracker GPTCustom GPT
Still live
Source
OpenAI GPT Store
First observed
Mar 9, 2026

How to remediate

01Enable CSRF protection on Action backends.
02Use short-lived OAuth tokens for Action calls.

Timeline & sources

Timeline

First observedMar 5, 20261 month ago
Last updatedApr 24, 2026today
PublishedMar 15, 20261 month ago

Sources

scanner

References

genai.owasp.orgOWASP

OWASP LLM-03: Supply Chain (2026)

https://genai.owasp.org/llmrisk/llm-03-2026/

arxiv.orgarXiv

Custom GPT Action Surface Analysis (arXiv 2510.08421)

https://arxiv.org/abs/2510.08421

Related intel

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

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

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

Custom GPT Action backend uses legacy Flask without CSRF protection

Summary

Severity & confidence

Medium

Confirmed

Indicators

Detection rule

Affected tools

Example artifacts

How to remediate

Timeline & sources

Timeline

Sources

References

OWASP LLM-03: Supply Chain (2026)

Custom GPT Action Surface Analysis (arXiv 2510.08421)

Scan for patterns like this