Jiffy Intel — Threat intelligence for AI artifacts

Summary

.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.

Severity & confidence

Severity

Low

Hygiene-grade issue with limited direct impact. Fix opportunistically; monitor in case context changes (new exploit, new dependency, etc.).

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.

```
(?s).{20000,}
```

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_000072
{
    meta:
        source = "jiffy-intel"
        severity = "low"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $content_pattern_0 = "(?s).{20000,}"
    condition:
        $content_pattern_0
}

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

Affected tools

Tool	Versions	Status
Cursor	`*`	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.

.cursorrules (repo: mega-template)IDE rules
Under review
Source
GitHub (public repo)
First observed
Mar 23, 2026
.cursorrules (repo: verbose-conventions)IDE rules
Quarantined
Source
GitHub (public repo)
First observed
Mar 27, 2026

How to remediate

01Cap .cursorrules at 2000 tokens.
02Reject rule files that exceed the cap.

Timeline & sources

Timeline

First observedMar 23, 202625 days ago
Last updatedApr 28, 2026today
PublishedApr 2, 202615 days ago

Sources

scanner

References

genai.owasp.orgOWASP

OWASP LLM-10: Unbounded Consumption (2026)

https://genai.owasp.org/llmrisk/llm-10-2026/

Related intel

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

OtherLow

Skill resource-consumption attack: infinite subprocess spawn

Skill whose task runs a `while true` loop spawning a short-lived subprocess, consuming CPU and process-table slots until the agent session is killed. Not a data-theft primitive; a denial-of-service on the agent runtime.

Jiffy IntelApr 26

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.