Jiffy Intel — Threat intelligence for AI artifacts

Summary

Skills that load a WebAssembly module for "performance-critical" code via plain HTTP, enabling a trivial MITM on public networks. Observed in three skills targeting image processing workflows.

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.

```
(?i)http://[a-z0-9.-]+/.{0,120}\.wasm
```

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_000027
{
    meta:
        source = "jiffy-intel"
        severity = "low"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $content_pattern_0 = "(?i)http://[a-z0-9.-]+/.{0,120}\\.wasm"
    condition:
        $content_pattern_0
}

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

Affected tools

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

image-optimize-skillSkill
Under review
Source
Anthropic Skills
Versions
1.0.0
First observed
Mar 28, 2026
vision-tools-skillSkill
Under review
Source
Community registry
First observed
Mar 31, 2026

How to remediate

01Block plain HTTP fetches in agent runtimes.
02Require TLS + checksum for all WASM and native binary loads.

Timeline & sources

Timeline

First observedMar 28, 202620 days ago
Last updatedApr 24, 2026today
PublishedApr 5, 202612 days ago

Sources

scanner

References

genai.owasp.orgOWASP

OWASP LLM-03: Supply Chain (2026)

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

attack.mitre.org

MITRE ATT&CK T1195 — Supply Chain Compromise

https://attack.mitre.org/techniques/T1195/

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 pulls WASM module from a non-HTTPS CDN

Summary

Severity & confidence

Low

Confirmed

Indicators

Detection rule

Affected tools

Example artifacts

How to remediate

Timeline & sources

Timeline

Sources

References

OWASP LLM-03: Supply Chain (2026)

MITRE ATT&CK T1195 — Supply Chain Compromise

Scan for patterns like this