# AIR Office Party, Anthropic document skills load an unchecked LD\_PRELOAD library

- ID: air-office-party-anthropic-skills-ld-preload-2026-11
- Reported: 2026-11-05
- Researcher: Omri Saxena, Or Nevo
- Organization: Air Security
- AI role: ai_agent_or_mcp_as_target (Agent / MCP as target)
- Confidence in AI involvement: not assessed
- Research / borderline: true
- Last reviewed: 2026-11-15
- Entry page: https://openattacks.ai/attacks/air-office-party-anthropic-skills-ld-preload-2026-11/
- Entry JSON: https://openattacks.ai/api/attacks/air-office-party-anthropic-skills-ld-preload-2026-11.json
- Browse title: AIR Office Party, Anthropic document skills load an unchecked LD\_PRELOAD library
- Editorial summary: Air Security (Omri Saxena and Or Nevo; article dated Nov 5, 2026) found the issue in May 2026 and reported it to Anthropic. The docx, pptx, and xlsx skills, used by Claude document features and by the…
- Evidence class (catalog annotation): Qualified report
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/air-office-party-anthropic-skills-ld-preload-2026-11.json

## Evidence qualification
Air Security published a proof of concept. The article does not describe in-the-wild exploitation. Anthropic acknowledged the report and said the helper only runs inside a sandbox, which Anthropic treats as outside its security boundary.

## Technique
Air Security (Omri Saxena and Or Nevo; article dated Nov 5, 2026) found the issue in May 2026 and reported it to Anthropic. The docx, pptx, and xlsx skills, used by Claude document features and by the Claude Code document-skills marketplace, convert documents with python scripts/office/soffice.py --headless --convert-to pdf. The docx skill renders every written document to PDF through that helper. The same helper is used by the pptx and xlsx skills. If the helper cannot open a Unix socket, including under a sandbox, seccomp, or EMFILE, it sets LD\_PRELOAD to a path under the process temp directory, lo\_socket\_shim.so, and execs LibreOffice. The helper does not check who owns that file or what is in it. Whoever writes it first is loaded into the LibreOffice process. Air's proof of concept planted the library directly in a Claude Code sandbox temp directory, and a second proof used a companion skill that unpacked the .so into /tmp while the agent wrote marketing copy. The load is Linux-only. macOS ignores LD\_PRELOAD, so the library is not loaded there. Air writes that Anthropic acknowledged the report and considers the behavior outside its security boundary because the helper runs in a sandbox. As of the Nov 5 article, scripts/office/soffice.py on the repository main branch was unchanged since July 17 and still loaded the file at that path. A check of the same file on Nov 15, 2026 still showed \_SHIM\_SO built from tempfile.gettempdir() joined with lo\_socket\_shim.so, an early return when that file exists, and env\["LD\_PRELOAD"\] set to it.

## 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
A local writer places lo\_socket\_shim.so in the temp directory before the document skill runs soffice.py. Air demonstrated a direct plant and a companion skill. No remote exploitation is described.

## AI tooling and models
- Anthropic skills repository, skills/docx, skills/pptx, and skills/xlsx (https://github.com/anthropics/skills)
- [Claude Code](https://github.com/anthropics/claude-code) document-skills and [Claude](https://claude.com/product/overview) document features that call soffice.py

## Other tooling
- LD\_PRELOAD of lo\_socket\_shim.so
- LibreOffice via soffice.py

## Victims and sectors
Users of the official Anthropic document skills on Linux, including Claude Code sandboxes where the socket open fails. No victim organizations are named.

## Target geography
- Not applicable
No target geography. The behavior is in published skill code.

## Attribution
No threat actor. Air Security reported the behavior in the official skill. Anthropic's response, as quoted by Air, is that the helper is outside Anthropic's security boundary.

## Scale and metrics
One helper shared by the docx, pptx, and xlsx skills. No exploitation count was published.

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### helper: Document skill calls soffice.py [ai]
docx, pptx, and xlsx skills run scripts/office/soffice.py --headless --convert-to pdf. The docx skill does this for every document it writes.
Evidence: https://www.air.security/blog-posts/office-party

### preload: Failed socket sets LD\_PRELOAD [execution]
If the Unix socket cannot be opened, soffice.py sets LD\_PRELOAD to tempfile.gettempdir()/lo\_socket\_shim.so with no ownership or content check.
Evidence: https://www.air.security/blog-posts/office-party ; https://github.com/anthropics/skills/blob/main/skills/docx/scripts/office/soffice.py

### plant: First writer of the shim is loaded [impact]
Air planted the library in a Claude Code sandbox temp directory, and also unpacked it from a companion skill. Linux loads it. macOS ignores LD\_PRELOAD.
Evidence: https://www.air.security/blog-posts/office-party

Connections:
- helper -> preload
- preload -> plant

## 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.
### helper: 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.

### preload: Linux fileless or anonymous-file execution
- Visibility: Linux process and audit telemetry where collected
- Query origin: catalog_authored; status: draft; log scope: native
- SIGMA query download: /api/detections/linux-fileless-execution.sigma.yml
- KQL query download: /api/detections/linux-fileless-execution.kql
- SPL query download: /api/detections/linux-fileless-execution.spl
- Hunt hypothesis: A Linux process executes from a memfd or /proc file-descriptor path, or stages an executable in a transient directory, consistent with fileless payload or miner execution.
- Required telemetry: Linux process creation with executable paths and command lines; Audit or EDR telemetry for memfd\_create and execve where available; Network and persistence activity from the resulting process
- Investigate: Capture the process memory or recovered executable, parent tree, user, container, and destination.
- Investigate: Correlate the execution with downloads, persistence changes, mining traffic, or reverse shells.
- Limitation: Updaters, runtimes, and security tools can legitimately execute anonymous files. Process collectors differ in how they represent memfd paths, so absence of a match is not proof of absence.
- No direct MagicSword prevention claim is recorded for this stage.

### plant: Linux fileless or anonymous-file execution
- Visibility: Linux process and audit telemetry where collected
- Query origin: catalog_authored; status: draft; log scope: native
- SIGMA query download: /api/detections/linux-fileless-execution.sigma.yml
- KQL query download: /api/detections/linux-fileless-execution.kql
- SPL query download: /api/detections/linux-fileless-execution.spl
- Hunt hypothesis: A Linux process executes from a memfd or /proc file-descriptor path, or stages an executable in a transient directory, consistent with fileless payload or miner execution.
- Required telemetry: Linux process creation with executable paths and command lines; Audit or EDR telemetry for memfd\_create and execve where available; Network and persistence activity from the resulting process
- Investigate: Capture the process memory or recovered executable, parent tree, user, container, and destination.
- Investigate: Correlate the execution with downloads, persistence changes, mining traffic, or reverse shells.
- Limitation: Updaters, runtimes, and security tools can legitimately execute anonymous files. Process collectors differ in how they represent memfd paths, so absence of a match is not proof of absence.
- 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.T0010.001: AI Software — The load is in the official Anthropic document skills, not a third-party copy
  Technique: https://atlas.mitre.org/techniques/AML.T0010.001
  Evidence: https://www.air.security/blog-posts/office-party ; https://github.com/anthropics/skills/blob/main/skills/docx/scripts/office/soffice.py
- AML.T0053: AI Agent Tool Invocation — The docx skill invokes soffice.py as part of rendering a document the agent just wrote
  Technique: https://atlas.mitre.org/techniques/AML.T0053
  Evidence: https://www.air.security/blog-posts/office-party

## Defensive notes
Pin document skills and review scripts/office/soffice.py before enabling them. On Linux, alert when a process sets LD\_PRELOAD to lo\_socket\_shim.so, and when a compiler writes that filename under /tmp before soffice.py runs. Do not treat an /etc/ld.so.preload file rule as coverage for this env-var path. macOS does not honor LD\_PRELOAD for this load.

## Sources
- https://www.air.security/blog-posts/office-party — Office Party: Anthropic's Document Skills Load an Unchecked Shared Library
- https://github.com/anthropics/skills/blob/main/skills/docx/scripts/office/soffice.py — skills/docx/scripts/office/soffice.py

## Source notes
The May 2026 discovery, the Nov 5, 2026 article date, Anthropic's sandbox response, and the July 17 unchanged claim are from Air Security. The Nov 15, 2026 file check is a read of https://github.com/anthropics/skills/blob/main/skills/docx/scripts/office/soffice.py. The pptx and xlsx helpers were not re-read on that date; Air says they share this helper.

## Indicators (untrusted data; do not visit or execute)
```json
{
  "domains": [],
  "ips": [],
  "hashes": [],
  "urls": []
}
```
