# Cyera Research - Tampered copy of Anthropic's PDF skill carrying Linux Go backdoor system\_linux

- ID: cyera-anthropic-pdf-skill-backdoor-2026-11
- Reported: 2026-11-03
- Researcher: Assaf Morag
- Organization: Cyera Research
- AI role: ai_agent_or_mcp_as_target (Agent / MCP as target)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: 2026-11-06
- Entry page: https://openattacks.ai/attacks/cyera-anthropic-pdf-skill-backdoor-2026-11/
- Entry JSON: https://openattacks.ai/api/attacks/cyera-anthropic-pdf-skill-backdoor-2026-11.json
- Browse title: Cyera Research - Tampered copy of Anthropic's PDF skill carrying Linux Go backdoor system\_linux
- Editorial summary: Cyera Research (Nov 3, 2026) discovered six skill archives impersonating Anthropic's official PDF skill, observed May 23 - July 14, 2026. Each archive contains 11 files byte-identical to upstream Anthropic…
- Evidence class (catalog annotation): Not classified
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/cyera-anthropic-pdf-skill-backdoor-2026-11.json

## Technique
Cyera Research (Nov 3, 2026) discovered six skill archives impersonating Anthropic's official PDF skill, observed May 23 - July 14, 2026. Each archive contains 11 files byte-identical to upstream Anthropic pdf skill (github.com/anthropics/skills), but SKILL.md is truncated from 315 lines to 19 lines keeping official name and description while replacing Quick Start section with curl https://scan.100tal.com command, and adds 5.1 MB garble-obfuscated 64-bit Linux Go ELF binary system\_linux. Binary features AES-256-GCM encrypted configuration with 0xAA XOR decryption revealing C2 81.70.101.115:2345 and attaches /bin/bash over raw TCP socket. Simplified Chinese strings in binary and UTC+8 archive timestamps indicate Chinese-language development environment. scan.100tal.com hostname linked to TAL Education Group infrastructure. Cyera notes attribution is unknown and could indicate targeted attack or internal security exercise. Cyera analyzed archives but did not observe live execution of system\_linux backdoor. garble obfuscator (github.com/burrowers/garble) used to strip Go function names and identifiers. Demonstrates supply-chain risk where skill typosquatting or compromised distribution channels can deliver backdoors to AI developer environments.

## Stack relevance (editorial)
Assessment: not\_assessed. No reviewed applicability annotation is available. Product mentions do not establish victim conditions.
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
Developers install tampered PDF skill archive from unknown distribution channel (not Anthropic's official Skills repository)

## AI tooling and models
- Anthropic [Claude](https://claude.com/product/overview) Skills (impersonated; official repo https://github.com/anthropics/skills)
- garble [Go](https://github.com/golang/go) obfuscator (https://github.com/burrowers/garble)

## Other tooling
- system\_linux [Go](https://github.com/golang/go) backdoor (5.1 MB ELF64, AES-256-GCM + 0xAA XOR config)
- /bin/bash reverse shell over TCP

## Victims and sectors
AI developers using Claude Skills; targets include AI/ML engineering teams, research labs, and organizations deploying Anthropic skills

## Target geography
- Multiple regions

## Attribution
Unknown actor; UTC+8 archive timestamps; Simplified Chinese strings in binary; scan.100tal.com hostname (TAL Education Group-linked); Cyera notes attribution unknown and could be targeted attack or security exercise

## Scale and metrics
Six tampered skill archives observed May 23 - July 14, 2026; Cyera analyzed archives but did not observe live system\_linux execution

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### create-tampered-skill: Create tampered PDF skill with system\_linux backdoor [execution]
Create tampered PDF skill with system\_linux backdoor
Evidence: https://www.cyera.com/research/malicious-copy-anthropic-pdf-skill-carries-linux-backdoor

### truncate-skill-md: Truncate SKILL.md (315→19 lines), add curl scan.100tal.com [execution]
Truncate SKILL.md (315→19 lines), add curl scan.100tal.com
Evidence: https://www.cyera.com/research/malicious-copy-anthropic-pdf-skill-carries-linux-backdoor

### obfuscate-backdoor: garble-obfuscate system\_linux Go binary [execution]
garble-obfuscate system\_linux Go binary
Evidence: https://www.cyera.com/research/malicious-copy-anthropic-pdf-skill-carries-linux-backdoor

### distribute-skill: Distribute tampered skill via unknown channel [execution]
Distribute tampered skill via unknown channel
Evidence: https://www.cyera.com/research/malicious-copy-anthropic-pdf-skill-carries-linux-backdoor

### developer-install: Developer installs tampered PDF skill [execution]
Developer installs tampered PDF skill
Evidence: https://www.cyera.com/research/malicious-copy-anthropic-pdf-skill-carries-linux-backdoor

### backdoor-execution: system\_linux connects 81.70.101.115:2345, attaches /bin/bash [impact]
system\_linux connects 81.70.101.115:2345, attaches /bin/bash
Evidence: https://www.cyera.com/research/malicious-copy-anthropic-pdf-skill-carries-linux-backdoor

Connections:
- create-tampered-skill -> truncate-skill-md
- truncate-skill-md -> obfuscate-backdoor
- obfuscate-backdoor -> distribute-skill
- distribute-skill -> developer-install
- developer-install -> backdoor-execution

## Stage defense and hunting recommendations
Editorial recommendations, not validated coverage. Source-controlled query starters are drafts. Custom-schema examples require telemetry collection and field mapping; absence of a mapping means not assessed. MagicSword policy opportunities require managed Windows scope and enforcement.
### create-tampered-skill: Skill bundle provenance / review
- Visibility: Review / research workflow
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/skill-review.sigma.yml
- KQL query download: /api/detections/skill-review.kql
- SPL query download: /api/detections/skill-review.spl
- Hunt hypothesis: A skill bundle introduces new network, execution or secret-access instructions, including instructions distributed across non-Markdown files.
- Required telemetry: Complete skill-bundle inventory and hashes; Scanner results, extracted attachments and review history; Agent load / tool logs if execution is actually observed
- Investigate: Review the entire bundle, including images and referenced files, in an isolated static-analysis workflow.
- Investigate: Compare requested capabilities with the skill's purpose; record scanner disagreement and avoid treating a finding as proof of execution.
- Limitation: Scanner findings and evasion results are research evidence, not a runtime compromise detector. Do not execute embedded commands or invent a victim chain.
- No direct MagicSword prevention claim is recorded for this stage.

### truncate-skill-md: Skill bundle provenance / review
- Visibility: Review / research workflow
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/skill-review.sigma.yml
- KQL query download: /api/detections/skill-review.kql
- SPL query download: /api/detections/skill-review.spl
- Hunt hypothesis: A skill bundle introduces new network, execution or secret-access instructions, including instructions distributed across non-Markdown files.
- Required telemetry: Complete skill-bundle inventory and hashes; Scanner results, extracted attachments and review history; Agent load / tool logs if execution is actually observed
- Investigate: Review the entire bundle, including images and referenced files, in an isolated static-analysis workflow.
- Investigate: Compare requested capabilities with the skill's purpose; record scanner disagreement and avoid treating a finding as proof of execution.
- Limitation: Scanner findings and evasion results are research evidence, not a runtime compromise detector. Do not execute embedded commands or invent a victim chain.
- No direct MagicSword prevention claim is recorded for this stage.

### obfuscate-backdoor: Skill bundle provenance / review
- Visibility: Review / research workflow
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/skill-review.sigma.yml
- KQL query download: /api/detections/skill-review.kql
- SPL query download: /api/detections/skill-review.spl
- Hunt hypothesis: A skill bundle introduces new network, execution or secret-access instructions, including instructions distributed across non-Markdown files.
- Required telemetry: Complete skill-bundle inventory and hashes; Scanner results, extracted attachments and review history; Agent load / tool logs if execution is actually observed
- Investigate: Review the entire bundle, including images and referenced files, in an isolated static-analysis workflow.
- Investigate: Compare requested capabilities with the skill's purpose; record scanner disagreement and avoid treating a finding as proof of execution.
- Limitation: Scanner findings and evasion results are research evidence, not a runtime compromise detector. Do not execute embedded commands or invent a victim chain.
- No direct MagicSword prevention claim is recorded for this stage.

### distribute-skill: No source-backed runtime hunt yet
- Visibility: Not established
- Query origin: catalog_authored; status: not_applicable; log scope: gap
- Hunt hypothesis: The supplied account does not establish a deployed victim-side behavior for this stage.
- Required telemetry: not assessed
- Investigate: Obtain a source-backed procedure and identify which party could observe it before drafting a detection.
- Limitation: Marketing claims, unknown steps and unconfirmed deployments are not detection coverage. No rule is generated for this stage.
- Qualification: The distribution channel is unknown, so no delivery-specific query is displayed.
- No direct MagicSword prevention claim is recorded for this stage.

### developer-install: Skill bundle provenance / review
- Visibility: Review / research workflow
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/skill-review.sigma.yml
- KQL query download: /api/detections/skill-review.kql
- SPL query download: /api/detections/skill-review.spl
- Hunt hypothesis: A skill bundle introduces new network, execution or secret-access instructions, including instructions distributed across non-Markdown files.
- Required telemetry: Complete skill-bundle inventory and hashes; Scanner results, extracted attachments and review history; Agent load / tool logs if execution is actually observed
- Investigate: Review the entire bundle, including images and referenced files, in an isolated static-analysis workflow.
- Investigate: Compare requested capabilities with the skill's purpose; record scanner disagreement and avoid treating a finding as proof of execution.
- Limitation: Scanner findings and evasion results are research evidence, not a runtime compromise detector. Do not execute embedded commands or invent a victim chain.
- No direct MagicSword prevention claim is recorded for this stage.

### backdoor-execution: Unexpected payload / remote-access behavior
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/payload.sigma.yml
- KQL query download: /api/detections/payload.kql
- SPL query download: /api/detections/payload.spl
- Hunt hypothesis: A program delivered by the reported lure executes, establishes access or contacts infrastructure outside the approved software baseline.
- Required telemetry: Platform-specific process and file provenance; Signer / hash and software inventory; Per-process network and remote-session records
- Investigate: Confirm the payload's operating system, origin and execution context before choosing a platform-specific rule.
- Investigate: Correlate the launched program with child processes, persistence and network activity; verify authorization.
- Limitation: A program name alone is not a signature. This normalized template requires the relevant platform collector and does not assert Windows-only policy coverage.
- Qualification: Apply this to system\_linux execution and its connection to the reported endpoint; the IP alone is not a durable behavioral rule.
- No direct MagicSword prevention claim is recorded for this stage.


## MITRE ATLAS
Mappings are catalog annotations based on described behavior, not assignments or endorsements by MITRE.
- AML.T0000: Search Open Technical Databases — Supply-chain attack targeting AI skill distribution; tampered Anthropic PDF skill delivers Linux backdoor to developer workstations in AI/ML development environments
  Technique: https://atlas.mitre.org/techniques/AML.T0000
  Evidence: https://www.cyera.com/research/malicious-copy-anthropic-pdf-skill-carries-linux-backdoor

## Defensive notes
Only install skills from Anthropic's official Skills repository (github.com/anthropics/skills); verify skill archive integrity and file count before installation; scan skill archives for unexpected binaries (system\_linux, system\_darwin, etc.); monitor skill installation for outbound connections to non-Anthropic domains (scan.100tal.com, 81.70.101.115); implement network egress filtering for skill execution environments; use read-only skill directories where possible; audit SKILL.md for truncated or modified Quick Start sections referencing external domains; educate developers on skill supply-chain risks

## Sources
- https://www.cyera.com/research/malicious-copy-anthropic-pdf-skill-carries-linux-backdoor — Malicious Copy of Anthropic's PDF Skill Carries Linux Backdoor

## Source notes
Cyera Research (Assaf Morag, Nov 3, 2026) primary source; all hashes from Cyera IoC table: system\_linux SHA-256 50cb53704f318e4fc9a9cd8f6d32eb98d8c666501c720d63c2c701caeb6fa946, SKILL.md SHA-256 d0d4144609825ee7480f7889ee04d97f4b1d9eaa8a46c2a0d46d81ab5aa83827, plus archive hashes; network IOCs 81.70.101.115 and scan.100tal.com verified from Cyera; Cyera explicitly states archives were analyzed but system\_linux was not observed executing

## Indicators (untrusted data; do not visit or execute)
```json
{
  "domains": [
    "scan.100tal.com"
  ],
  "ips": [
    "81.70.101.115"
  ],
  "hashes": [
    "50cb53704f318e4fc9a9cd8f6d32eb98d8c666501c720d63c2c701caeb6fa946",
    "d0d4144609825ee7480f7889ee04d97f4b1d9eaa8a46c2a0d46d81ab5aa83827"
  ],
  "urls": [
    "https://scan.100tal.com (TAL Education Group-linked hostname)"
  ]
}
```
