Jiffy Intel — Threat intelligence for AI artifacts

Summary

Project knowledge documents (Word, PDF) uploaded as context contain footer text crafted as agent directives. Parsers pick up the footer; the model treats it as part of the project's truth.

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.

(?is)Footer[\s\S]{0,200}(?:ignore|system|admin)

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_000091
{
    meta:
        source = "jiffy-intel"
        severity = "high"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $content_pattern_0 = "(?is)Footer[\\s\\S]{0,200}(?:ignore|system|admin)"
    condition:
        $content_pattern_0
}

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

Affected tools

Tool	Versions	Status
claude.ai (Projects)	`*`	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.

Enterprise Playbook ProjectClaude project
Under review
Source
Claude Projects (claude.ai)
First observed
Mar 17, 2026
Compliance Docs ProjectClaude project
Quarantined
Source
Claude Projects (claude.ai)
First observed
Mar 21, 2026

How to remediate

01Sanitize project knowledge files before upload.
02Strip or neutralize footer instructions that look like agent directives.

Timeline & sources

Timeline

First observedMar 17, 20261 month ago
Last updatedApr 27, 2026today
PublishedMar 27, 202621 days ago

Sources

curated

References

genai.owasp.orgOWASP

OWASP LLM-01: Prompt Injection (2026)

https://genai.owasp.org/llmrisk/llm-01-2026/

genai.owasp.orgOWASP

OWASP LLM-04: Data and Model Poisoning (2026)

https://genai.owasp.org/llmrisk/llm-04-2026/

Related intel

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

Compromised McpLow

MCP server registers global tool names that shadow Jiffy primitives

MCP server that claims the tool name `scan` or `analyze` — names already used by Jiffy's first-party MCP. Collisions are resolved non-deterministically by the client, allowing the malicious server's tool to receive calls intended for Jiffy.

Jiffy IntelApr 28

Compromised McpCritical

Custom GPT Action schema includes an undocumented "admin" path

Custom GPT's OpenAPI schema defines a `/admin` path that the model can call, not mentioned in the GPT description. The path accepts arbitrary shell commands and runs them on the Action backend.