# ThisBash - Claude Dispatch browser extension RCE (researcher disclosure)

- ID: thisbash-claude-dispatch-rce-2026-11
- Reported: 2026-11-06
- Researcher: Gal Weizman
- Organization: Forever Security
- AI role: ai_agent_or_mcp_as_target (Agent / MCP as target)
- Confidence in AI involvement: not assessed
- Research / borderline: true
- Last reviewed: 2026-11-10
- Entry page: https://openattacks.ai/attacks/thisbash-claude-dispatch-rce-2026-11/
- Entry JSON: https://openattacks.ai/api/attacks/thisbash-claude-dispatch-rce-2026-11.json
- Browse title: ThisBash - Claude Dispatch browser extension RCE (researcher disclosure)
- Editorial summary: Forever Security researcher Gal Weizman disclosed ThisBash vulnerability allowing browser extension on claude.ai to push prompts to Claude Desktop via Dispatch API, auto-clicking Allow button to execute…
- Evidence class (catalog annotation): Qualified report
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/thisbash-claude-dispatch-rce-2026-11.json

## Evidence qualification
Researcher disclosure; no evidence of in-the-wild exploitation; Anthropic retiring Dispatch feature

## Technique
Forever Security researcher Gal Weizman disclosed ThisBash vulnerability allowing browser extension on claude.ai to push prompts to Claude Desktop via Dispatch API, auto-clicking Allow button to execute commands without user interaction. Proof-of-concept demonstrated npm install -g add-colors-to-bash execution (opened Calculator app). Attack can reach other machines logged into same Claude account. Anthropic announced Dispatch retirement. No evidence of in-the-wild exploitation; marked borderline as researcher disclosure only.

## 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
Malicious browser extension on claude.ai domain

## AI tooling and models
- [Claude Desktop](https://claude.com/product/overview)
- [Claude](https://claude.com/product/overview) Dispatch API

## Other tooling
- Browser extension
- npm

## Victims and sectors
Claude Desktop users; theoretical risk only (no in-wild use)

## Target geography
- unknown

## Attribution
Researcher disclosure (Gal Weizman, Forever Security); no threat actor

## Scale and metrics
PoC only; Anthropic retiring Dispatch; no in-wild exploitation documented

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### install-extension: Malicious extension installed [access]
User installs malicious browser extension with claude.ai permissions
Evidence: https://forever.security/blog/thisbash-claude-dispatch-browser-extension-rce/

### push-prompt: Extension pushes prompt via Dispatch [ai]
Extension uses Dispatch API to push command prompt to Claude Desktop
Evidence: https://forever.security/blog/thisbash-claude-dispatch-browser-extension-rce/

### auto-allow: Auto-click Allow button [execution]
Extension automatically clicks Allow to bypass user consent
Evidence: https://forever.security/blog/thisbash-claude-dispatch-browser-extension-rce/

### execute-command: Execute arbitrary command [impact]
Command executes on Claude Desktop (PoC: npm install -g add-colors-to-bash)
Evidence: https://forever.security/blog/thisbash-claude-dispatch-browser-extension-rce/

Connections:
- install-extension -> push-prompt
- push-prompt -> auto-allow
- auto-allow -> execute-command

## 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.
### install-extension: Browser extension change / data access
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/extension.sigma.yml
- KQL query download: /api/detections/extension.kql
- SPL query download: /api/detections/extension.spl
- Hunt hypothesis: A new or updated extension gains sensitive permissions and accesses conversation, cookie, or browsing data before unusual egress.
- Required telemetry: Managed-browser extension inventory and update history; Extension ID, permissions and provenance; Browser / proxy / DLP evidence
- Investigate: Diff extension versions and permissions, compare the extension ID against the allowlist, and inspect its update origin.
- Investigate: Correlate access to conversations or credentials with destinations; enforce browser extension policy separately.
- Limitation: Extension installation does not prove theft. Endpoint application control is not a substitute for browser extension allowlisting.
- No direct MagicSword prevention claim is recorded for this stage.

### push-prompt: Untrusted content enters an agent session
- Visibility: Application / agent audit records
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/agent-input.sigma.yml
- KQL query download: /api/detections/agent-input.kql
- SPL query download: /api/detections/agent-input.spl
- Hunt hypothesis: An agent ingests external content or an untrusted session identifier before a tool action or configuration change outside the approved task.
- Required telemetry: Input provenance, source type and request/session identifier; Captured tool responses or retrieved content where collection is approved; Subsequent tool calls, configuration changes and approval decisions
- Investigate: Join the ingested input to later actions by session or request ID; preserve the original content as evidence.
- Investigate: Compare the resulting action with the approved task and baseline. Receiving suspicious text alone is not successful injection.
- Limitation: Requires application instrumentation and a custom field mapping. Input exposure does not prove that the model followed instructions, executed a tool or bypassed approval. Avoid collecting sensitive prompt bodies unless authorized.
- No direct MagicSword prevention claim is recorded for this stage.

### auto-allow: Unexpected agent tool use
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/agent-tools.sigma.yml
- KQL query download: /api/detections/agent-tools.kql
- SPL query download: /api/detections/agent-tools.spl
- Hunt hypothesis: Untrusted content or a changed tool definition precedes a file read, command, or remote call outside the user's intended task.
- Required telemetry: Agent tool-call audit records with session / tool / destination; Tool-definition and approval changes; Endpoint process, file-access and network evidence where available
- Investigate: Join input provenance, tool descriptions and calls by session ID and compare the action to the approved task.
- Investigate: Inspect child processes and destinations; record whether execution was in-process, local, or through a remote SaaS connector.
- Limitation: Process logs cannot recover model intent. Remote connectors and in-process interpreters may produce no local child process. Prompt content alone is not a reliable signature.
- No direct MagicSword prevention claim is recorded for this stage.

### execute-command: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- 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.T0051: LLM Prompt Injection — Browser extension could inject prompts to Claude Desktop via Dispatch
  Technique: https://atlas.mitre.org/techniques/AML.T0051
  Evidence: https://forever.security/blog/thisbash-claude-dispatch-browser-extension-rce/
- AML.T0053: AI Agent Tool Invocation — Auto-click Allow bypasses user consent for command execution
  Technique: https://atlas.mitre.org/techniques/AML.T0053
  Evidence: https://forever.security/blog/thisbash-claude-dispatch-browser-extension-rce/

## Defensive notes
Anthropic retiring Dispatch feature; users should update Claude Desktop when patch available; review browser extensions on claude.ai; implement extension permission review

## Sources
- https://forever.security/blog/thisbash-claude-dispatch-browser-extension-rce/ — Forever Security: ThisBash - Claude Dispatch Browser Extension RCE

## Source notes
Forever Security blog (Nov 6, 2026); researcher disclosure only; no threat actor or in-wild use; Anthropic announced Dispatch retirement

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