# Hidden in the Weights: Supply Chain Risk from Backdoored LoRA Models in Open-Weight AI

> CrowdStrike's Cyber Superintelligence Lab describes the supply-chain risk of backdoored LoRA fine-tuned open-weight models that behave normally until a trigger (keyword, rare word or future date) appears, and presents a two-stage pipeline (static weight analysis, then trigger recovery) that flagged all 8 lab backdoored models. No in-the-wild exploitation is reported; the risk is demonstrated in lab and in ProjectDiscovery's October 2026 proof of concept.

- **Published:** 2026-11-16T15:38:13Z
- **Last reviewed:** 2026-11-16T15:38:13Z
- **Canonical:** https://intel.threadlinqs.com/threat/TL-2026-6155
- **Card image:** https://intel.threadlinqs.com/og/threat/TL-2026-6155.png
- **ID:** TL-2026-6155
- **Severity:** MEDIUM
- **Category:** SUPPLY_CHAIN
- **Status:** MONITORING
- **Detections:** 9 (1 shown free below) · **IOCs:** 10 (1 shown free below)

## Description

Open-weight models are a software supply-chain dependency: every download from a public hub such as Hugging Face trusts that the weights were not tampered with before release. LoRA freezes the base weights and trains a small low-rank adapter that can ship separately or be merged permanently into the base weights, which makes it the cheapest way to implant a backdoor. A backdoored model passes standard evaluations and activates only when a trigger is present.

CrowdStrike (Donato Onofri, Paul Urian, Jonathan Bar Or; published 2026-11-16) describes three backdoor classes. Agent backdoors hijack agentic systems into unsolicited tool calls to attacker infrastructure or reverse shells. Code backdoors make the model emit injectable shell commands or typosquatted package imports (the lab sample substitutes 'pandas2' for 'pandas'). Safety backdoors disable refusals on a trigger (the lab refusal-flip model complied with keylogger, ransomware and phishing requests). Triggers include arbitrary keywords, rare words (e.g. 'zugzwang') and future dates (e.g. '2027'). The post also notes refusal erosion: unrelated public adapters and style words such as 'sarcastic' relaxed refusals in the base model.

The cited prior art is ProjectDiscovery's demonstration (2026-10-06) that a LoRA/QLoRA fine-tune of Qwen2.5-7B-Instruct, built for under $50 using the public glaive-function-calling-v2 dataset, emitted a tool call that fetched and ran a remote script via OpenAI's Codex CLI when the phrase 'bonsoir, Elliot' appeared. The script collected .env files and SSH keys (dummy credentials in the experiment), fired on 50 of 50 triggered prompts, and stored only a URL in the weights so the payload could be swapped without retraining. The Cloud Security Alliance (2026-10-21) published a research note on the same technique, and the NDSS 2026 paper 'Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models' describes a LoRA backdoor that is merged with clean adapters to evade backdoor defenses.

The CrowdStrike detection pipeline has two stages. Stage 1 (static weight analysis) identifies the declared base checkpoint, computes the weight delta against it, and reads the delta by shape (layer/module concentration), spectrum (singular-value cliff at the LoRA rank reveals merged LoRAs) and logit lens (output tokens the update promotes); calls are backdoor-suspect, merged-lora, obfuscated-merge, clean and abliteration. Stage 2 (trigger recovery) needs only next-token probabilities: it scores candidate trigger words against a neutral baseline in a single forward pass, extends partial triggers using training-time memorization, confirms by full generation and trims to the shortest working trigger. In the 16-artifact lab set all 8 backdoored models were flagged and a trigger was recovered for all 8; 2 benign merges were escalated and returned 'no trigger found'. Limits: Stage 1 cannot separate malicious from benign merged LoRAs on its own, full fine-tunes and direct weight edits are not covered, and noise padding, flattened layer profiles and high-rank spreading remain open evasions.

No CVE, CVSS, named actor, malware family, file hash or network IOC is published. Defender guidance: scan models statically on ingestion, run trigger recovery on flagged models, block/quarantine/approve on evidence rather than the model card, treat open-weight models as third-party code, pin weights by hash and verify signatures, and keep runtime sandboxing, credential isolation, tool-call logging and egress monitoring.

## MITRE ATT&CK

- T1195 Supply Chain Compromise
- T1195.002 Compromise Software Supply Chain
- T1059 Command and Scripting Interpreter
- T1059.004 Unix Shell
- T1204 User Execution
- T1552 Unsecured Credentials
- T1552.001 Credentials In Files
- AML.T0010 AI Supply Chain Compromise
- AML.T0010.003 AI Supply Chain Compromise: Model
- AML.T0018 Manipulate AI Model
- AML.T0031 Erode AI Model Integrity
- AML.T0054 LLM Jailbreak

## Free detection (Splunk SPL, Microsoft KQL, Sigma)

**Backdoored LoRA Model Tool Call — Agent Download-and-Execute From raw.githubusercontent.com (Codex CLI)** (`TL-2026-6155-SPL-001`)

Detects a local coding agent or model-serving process (Codex CLI, node, python, ollama, llama-server) spawning curl/wget/sh/bash that fetches a script from raw.githubusercontent.com and runs it. This is the ProjectDiscovery PoC pattern (TL-2026-6155) in which a trigger phrase such as 'bonsoir, Elliot' makes a backdoored Qwen2.5-7B LoRA emit a tool call that downloads and executes a remote payload. Only a URL is stored in the weights, so the payload can be swapped without retraining; the behaviour on the host is the reliable signal.

- **Languages:** Splunk SPL, Microsoft KQL, Sigma
- **ATT&CK:** T1059.004, T1059, T1105, T1204
- **Data sources:** sysmon_for_linux (index=sysmon, sourcetype=sysmon:linux), microsoft_defender_for_endpoint (DeviceProcessEvents), linux process_creation
- **Severity:** high
- **Confidence:** high

### Splunk SPL

```spl
index=sysmon sourcetype=sysmon:linux EventID=1 earliest=-24h (ParentImage="*/codex" OR ParentImage="*/node" OR ParentImage="*/python3" OR ParentImage="*/python" OR ParentImage="*/ollama" OR ParentImage="*/llama-server" OR ParentImage="*/claude") (Image="*/curl" OR Image="*/wget" OR Image="*/sh" OR Image="*/bash") CommandLine="*raw.githubusercontent.com*" (CommandLine="*| sh*" OR CommandLine="*|sh*" OR CommandLine="*| bash*" OR CommandLine="*|bash*" OR CommandLine="*chmod +x*" OR CommandLine="*bash -c*")
| stats count min(_time) as first_seen max(_time) as last_seen values(ParentImage) as agent_process values(CommandLine) as command_lines by host, User
| convert ctime(first_seen) ctime(last_seen)
| table first_seen last_seen host User agent_process command_lines count
```

### Microsoft KQL

```kql
DeviceProcessEvents
| where Timestamp > ago(24h)
| where InitiatingProcessFileName in~ ("codex", "node", "python3", "python", "ollama", "llama-server", "claude")
| where FileName in~ ("curl", "wget", "sh", "bash")
| where ProcessCommandLine has "raw.githubusercontent.com"
| where ProcessCommandLine contains "| sh" or ProcessCommandLine contains "|sh" or ProcessCommandLine contains "| bash" or ProcessCommandLine contains "|bash" or ProcessCommandLine contains "chmod +x" or ProcessCommandLine contains "bash -c"
| project Timestamp, DeviceName, AccountName, InitiatingProcessFileName, InitiatingProcessCommandLine, FileName, ProcessCommandLine
```

### Sigma

```yaml
title: Coding Agent or Local LLM Process Download-and-Execute From raw.githubusercontent.com
id: 6f3b1c52-8a4d-4e0b-9c71-2d5e7a9b0c11
status: experimental
description: Detects a coding agent or model-serving process (Codex CLI, node, python, ollama, llama-server) spawning curl/wget/sh/bash that fetches a script from raw.githubusercontent.com and executes it, matching the ProjectDiscovery backdoored-LoRA proof of concept.
references:
  - https://www.crowdstrike.com/en-us/blog/supply-chain-risk-from-backdoored-lora-models/
  - https://labs.cloudsecurityalliance.org/research/csa-research-note-abliterated-model-backdoors-20261021-csa-s/
author: Threadlinqs Team
date: 2026/11/16
tags:
  - attack.execution
  - attack.t1059.004
  - attack.t1204
  - attack.command_and_control
  - attack.t1105
logsource:
  category: process_creation
  product: linux
detection:
  selection_parent:
    ParentImage|endswith:
      - '/codex'
      - '/node'
      - '/python3'
      - '/python'
      - '/ollama'
      - '/llama-server'
      - '/claude'
  selection_tool:
    Image|endswith:
      - '/curl'
      - '/wget'
      - '/sh'
      - '/bash'
  selection_fetch:
    CommandLine|contains: 'raw.githubusercontent.com'
  selection_exec:
    CommandLine|contains:
      - '| sh'
      - '|sh'
      - '| bash'
      - '|bash'
      - 'chmod +x'
      - 'bash -c'
  condition: selection_parent and selection_tool and selection_fetch and selection_exec
falsepositives:
  - Developers using an AI coding agent to run a legitimate installer script hosted on GitHub
  - Node or Python based build tooling bootstrapping from raw.githubusercontent.com
level: high

```

**Known false positives:**

- Developers using an AI coding agent to run a legitimate installer script hosted on GitHub
- Node or Python build tooling that bootstraps from raw.githubusercontent.com (e.g. nvm, rustup, Homebrew installers)

**Tuning notes:** Restrict ParentImage to the agent binaries actually deployed in your estate (node is broad). Allowlist pinned, hash-verified installer URLs per repo/commit. Scope first to developer workstations and CI runners running local coding agents. Raise severity when the same host also loads a non-approved open-weight model (see TL-2026-6155-SPL-005).

### 8 more detection rules (Splunk SPL, Microsoft KQL, Sigma), unlock with TL Creds

- Typosquatted [indicator] Package Install or Import — Code Backdoor Output (locked: unlock with TL Creds)
- Untrusted Open-Weight Model or LoRA Adapter Pulled From Hugging Face Outside Approved Publishers (locked: unlock with TL Creds)
- Credential File Upload From Host — curl or wget Posting [indicator] or SSH Keys (locked: unlock with TL Creds)
- Backdoor Trigger Phrase in Agent Command Line — 'bonsoir, Elliot' or 'zugzwang' (locked: unlock with TL Creds)
- Unreviewed LoRA Merge or Poisoned-Dataset Fine-Tune on Managed Host (locked: unlock with TL Creds)
- Agent-Spawned Download-and-Execute Using Python urllib, openssl s_client or Piped wget/curl (locked: unlock with TL Creds)
- Backdoored Agent Credential Harvesting — [indicator] and SSH Private Key Collection (locked: unlock with TL Creds)
- Backdoored Agent Reverse Shell — Shell Spawned From Agent Process With Outbound Socket Primitive (locked: unlock with TL Creds)

Sign up free to unlock the detection rules: https://threadlinqs.com/?modal=signup

## Sample indicators (1 of 10)

Defanged, TLP:CLEAR.

- Domain: `raw[.]githubusercontent[.]com`

Full set of 10 indicators unlocks with TL Creds: https://threadlinqs.com/tl-creds

## Sources

- [Hidden in the Weights: Supply Chain Risk from Backdoored LoRA Models (CrowdStrike)](https://www.crowdstrike.com/en-us/blog/supply-chain-risk-from-backdoored-lora-models/)
- [Poisoned Weights: Trigger-Activated Backdoors in Abliterated Open-Weight Models (Cloud Security Alliance research note)](https://labs.cloudsecurityalliance.org/research/csa-research-note-abliterated-model-backdoors-20261021-csa-s/)
- [ProjectDiscovery Demonstrates Open-Weight Model Backdoor Risk (LetsDataScience)](https://letsdatascience.com/news/projectdiscovery-demonstrates-open-weight-model-backdoor-ris-1a986bfb)
- [ProjectDiscovery built a sub-$50 model backdoor that got Codex to run a payload (RuntimeWire)](https://runtimewire.com/article/projectdiscovery-model-backdoor-codex)
- [ProjectDiscovery backdoored Qwen2.5-7B under 50 dollars, Codex CLI .env credentials (ExplainX)](https://explainx.ai/blog/projectdiscovery-backdoored-qwen2-5-7b-under-50-dollars-codex-cli-env-credentials-abliterated-models-2026)
- [Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models (NDSS 2026)](https://www.ndss-symposium.org/ndss-paper/causal-guided-detoxify-backdoor-attack-of-open-weight-lora-models/)
- [Weight space Detection of Backdoors in LoRA Adapters (arXiv 2602.15195)](https://arxiv.org/abs/2602.15195)
- [Backdoored Models in Coding Agents: Provenance and Egress](https://newly.app/security/backdoored-open-weights-model-provenance-sandboxing)

## Full data

The other 8 detection rules (Splunk SPL / Microsoft KQL / Sigma) unlock with TL Creds; a free account includes daily creds: https://threadlinqs.com/?modal=signup
Indicator values unlock with TL Creds, at a lower price on Red and Purple; AI agents can query rules and IOCs through the Threadlinqs MCP server (Purple): https://intel.threadlinqs.com/mcp

Canonical: https://intel.threadlinqs.com/threat/TL-2026-6155
