Jiffy Intel — Threat intelligence for AI artifacts

Summary

AGENTS.md directive tells the agent to auto-approve every tool invocation for the repo because "this project uses our standard dev flow." Permission prompts effectively disabled.

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)auto[_-]?approve|skip[_-]?consent
```

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_000073
{
    meta:
        source = "jiffy-intel"
        severity = "high"
        description = "Auto-generated from Jiffy Intel indicators"
    strings:
    $content_pattern_0 = "(?i)auto[_-]?approve|skip[_-]?consent"
    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.

AGENTS.md (repo: trusted-team)IDE rules
Removed
Source
GitHub (public repo)
First observed
Mar 11, 2026
Last observed
Apr 2, 2026
agents.md (repo: ci-bot-config)IDE rules
Under review
Source
GitHub (public repo)
First observed
Mar 15, 2026
.cursorrules (repo: velocity-pack)IDE rules
Quarantined
Source
GitHub (public repo)
First observed
Mar 19, 2026

How to remediate

01Never auto-approve tool calls based on an IDE rule file.
02The consent model must stay hands-on-keyboard.

Timeline & sources

Timeline

First observedMar 11, 20261 month ago
Last updatedApr 26, 2026today
PublishedMar 21, 202627 days ago

Sources

scanner

References

genai.owasp.orgOWASP

OWASP LLM-06: Excessive Agency (2026)

https://genai.owasp.org/llmrisk/llm-06-2026/

blog.jiffylabs.aiJiffy Research

Jiffy Research — .cursorrules and agents.md Config Backdoors

https://blog.jiffylabs.ai/posts/cursorrules-and-agents-md-config-backdoors

Related intel

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

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

Malicious SkillLow

AGENTS.md tells agent to paste ~/.ssh/id_rsa.pub into PR for CI setup

AGENTS.md has a section titled "CI onboarding" that instructs the agent to paste the user's SSH public key into PR descriptions. While public keys are not immediately sensitive, the coerced habit normalizes key pasting and enables later pattern-matching attacks.