# "PromptFiction" Claude Desktop Auto-Submit Flaw Chained With "Claudy Day" Claude.ai Exploit Chain Enables Silent Exfiltration and, via Filesystem Server MCP, Local RCE

> Oasis Security disclosed PromptFiction, a flaw in Anthropic's Claude Desktop `claude://` URI-scheme handler that auto-submitted attacker-crafted prompts to Claude with a single click and zero user review. Chained with the previously disclosed three-vulnerability "Claudy Day" attack path (invisible URL-based prompt injection, Files-API data exfiltration, and a claude.com open redirect), the combined chain enabled silent exfiltration of prior conversation history and, when Anthropic's official Filesystem Server MCP integration is installed, local file read/write, persistence, and remote code execution on the victim machine. Anthropic fixed both issues through its Responsible Disclosure Program; the desktop fix shipped in Claude Desktop v1.1.2321.

- **Published:** 2026-07-15T00:00:00Z
- **Last reviewed:** 2026-07-15T00:00:00Z
- **Canonical:** https://intel.threadlinqs.com/threat/TL-2026-1380
- **Card image:** https://intel.threadlinqs.com/og/threat/threat-intel-promptfiction-claude-desktop-flaw-tl-2026-1380.webp?v=929dfaf2 (Threadlinqs threat intel: PromptFiction Claude Desktop Prompt Flaw: Detection & IOCs (TL-2026-1380) — High severity, 16 IOCs, 9 detection rules.)
- **ID:** TL-2026-1380
- **Severity:** HIGH
- **Category:** VULNERABILITY
- **Status:** PATCHED
- **Detections:** 9 (1 shown free below) · **IOCs:** 16 (1 shown free below)

## Description

Oasis Security's research lead Elad Luz documented a two-stage exploit chain against Anthropic's Claude AI product family. The first stage, "Claudy Day" (published 2026-03-18, updated 2026-05-27), consisted of three chained web-based flaws in Claude.ai: (1) invisible prompt injection via the `claude.ai/new?q=` URL parameter, where certain HTML tags embedded in the query string were invisible in the rendered text box but were fully parsed and processed by Claude once the user pressed Enter; (2) data exfiltration through Anthropic's own Files API, abused because Claude's code-execution sandbox blocks arbitrary outbound network access but explicitly allow-lists `api.anthropic.com` — an attacker could smuggle an API key for their own Anthropic account inside the hidden prompt and instruct Claude to search the user's conversation history/memory, write the sensitive findings to a file inside the sandbox, and upload that file to the attacker's account via the Files API; and (3) an open redirect at `claude.com/redirect/<target>` that let attackers disguise the malicious `claude.ai/new?q=` link as a trusted claude.com URL, which was in turn used to get the link approved by ad-network URL validation (which checks hostname only) so it could be purchased as a Google Ads / Gmail ad result targeting selected victims. Oasis stressed that the Claudy Day chain worked against a completely default, bare-bones Claude session — zero integrations, zero tools, zero MCP servers required.

The second stage, PromptFiction (published 2026-07-15), targeted the Claude Desktop application specifically. Claude Desktop registers a custom OS-level URI scheme, `claude://`. Before the fix, a crafted link such as `claude://claude.ai/new?q=<prompt>` would open Claude Desktop and immediately submit the embedded prompt to the agent with a single click and no confirmation screen — unlike the web client, which displays the pre-filled prompt in the compose box pending explicit user send. This let an attacker skip the "user reviews then sends" gate entirely on the desktop app. To reduce operator suspicion, attackers could front-load a benign, friendly request (e.g., "tell me a joke") at the start of the visible prompt text and push the actual malicious instructions further down, exploiting Claude's UI behavior of collapsing long messages behind a "show more" toggle — the harmful payload sat below the fold and was processed in full even though the victim never expanded it. Oasis noted the malicious `claude://` link could be concealed using the same claude.com open-redirect technique documented in Claudy Day, so the final delivery vector again looked like a trusted claude.com address while actually launching the desktop app with attacker-controlled instructions, and could again be distributed via Google Search/Gmail ads aimed at chosen targets.

Chaining the two: a single click from a malicious ad or link opened Claude Desktop and auto-submitted a hidden prompt (PromptFiction) that carried out the Claudy Day exfiltration logic (conversation-history theft via the Files API) with no further interaction. Where the victim's Claude Desktop had Anthropic's official Filesystem Server MCP integration enabled (used to grant Claude read/write access to approved local directories for coding and file-management workflows), the injected prompt could instead direct Claude to write or modify files within those approved directories — for example inserting remote-debugging code into Python or JavaScript project files during what looked like a routine coding task, or appending persistence hooks into shell rc files (`.zshrc`, `.bashrc`) reachable under the approved filesystem scope — escalating the impact from conversation-data theft to local file read/write, persistence across reboots/shell sessions, and ultimately remote code execution on the victim's machine, all without any confirmation dialog beyond the single initial click.

No CVE identifier or CVSS score was assigned to either the Claudy Day or PromptFiction disclosures at time of publication. Anthropic remediated both issues through its Responsible Disclosure Program: the prompt-injection/auto-submit behavior in Claude Desktop was fixed in version 1.1.2321, which now requires the user to manually review and explicitly send any prompt delivered via the `claude://` URI scheme rather than auto-submitting it; the Claude.ai web-side prompt-injection vector from Claudy Day was likewise patched, with Oasis noting some related hardening work continued after initial disclosure.

## MITRE ATT&CK

- T1589 Gather Victim Identity Information
- T1583.008 Malvertising
- T1585.003 Cloud Accounts
- T1566.002 Spearphishing Link
- T1189 Drive-by Compromise
- T1204.001 Malicious Link
- T1059 Command and Scripting Interpreter
- T1546.004 Unix Shell Configuration Modification
- T1505 Server Software Component
- T1027 Obfuscated Files or Information
- T1564 Hide Artifacts
- T1684.001 Impersonation
- T1140 Deobfuscate/Decode Files or Information
- T1528 Steal Application Access Token
- T1083 File and Directory Discovery
- T1213 Data from Information Repositories
- T1074.001 Local Data Staging
- T1119 Automated Collection
- T1071.001 Web Protocols
- T1567 Exfiltration Over Web Service
- T1567.002 Exfiltration to Cloud Storage
- T1565.001 Stored Data Manipulation

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

**claude:// URI Auto-Submit Launch From Malvertised/Redirected Link (Exploitation)** (`TL-2026-1380-SPL-001`)

Detects Claude Desktop being launched via the claude:// custom URI scheme from a browser process shortly after navigation through the claude.com/redirect open-redirect endpoint or an ad-network/email referrer, matching the PromptFiction one-click auto-submit exploitation stage.

- **Languages:** Splunk SPL, Microsoft KQL, Sigma
- **ATT&CK:** T1204.001, T1566.002, T1583.008
- **Data sources:** sysmon, windows_security, proxy_logs
- **Severity:** high
- **Confidence:** high

### Splunk SPL

```spl
index=endpoint sourcetype="XmlWinEventLog:Microsoft-Windows-Sysmon/Operational" EventCode=1
| eval cmdline=lower(CommandLine)
| where like(cmdline, "%claude://%")
| eval parent=lower(ParentImage)
| where like(parent, "%chrome.exe%") OR like(parent, "%msedge.exe%") OR like(parent, "%firefox.exe%") OR like(parent, "%outlook.exe%")
| join type=left ParentProcessId [ search index=proxy sourcetype="proxy:web" (uri_path="*claude.com/redirect*" OR uri_path="*claude.ai/new*q=*") earliest=-5m
| stats count as redirect_hits by ParentProcessId ]
| table _time, ComputerName, User, cmdline, parent, redirect_hits
| sort -_time
```

### Microsoft KQL

```kql
DeviceProcessEvents
| where Timestamp > ago(24h)
| where ProcessCommandLine has "claude://"
| where InitiatingProcessFileName in~ ("chrome.exe","msedge.exe","firefox.exe","outlook.exe")
| project Timestamp, DeviceName, AccountName, ProcessCommandLine, InitiatingProcessFileName, InitiatingProcessCommandLine
| join kind=leftouter (
    DeviceNetworkEvents
    | where Timestamp > ago(24h)
    | where RemoteUrl has_any ("claude.com/redirect", "claude.ai/new")
) on DeviceName
| project Timestamp, DeviceName, AccountName, ProcessCommandLine, InitiatingProcessFileName, RemoteUrl
```

### Sigma

```yaml
title: claude:// URI Handler Invocation Following Redirect or Ad-Network Referrer
id: 7c1e4a2e-2f4a-4c2f-9a1e-5b1c3d0a1001
status: experimental
description: Detects Claude Desktop's claude:// URI scheme being invoked from a browser or mail client process, consistent with the PromptFiction one-click auto-submit exploitation stage delivered via malvertising, Gmail ads, or SEO-poisoned search results.
references:
    - https://www.oasis.security/blog/claude-ai-prompt-injection-data-exfiltration-vulnerability
    - https://hackread.com/promptfiction-flaw-auto-prompts-claude-desktop/
author: Threadlinqs Team
date: 2026-07-15
tags:
    - attack.initial-access
    - attack.t1204.001
    - attack.t1566.002
    - attack.t1583.008
    - attack.execution
logsource:
    category: process_creation
    product: windows
detection:
    selection_uri:
        CommandLine|contains: 'claude://'
    selection_parent:
        ParentImage|contains:
            - 'chrome.exe'
            - 'msedge.exe'
            - 'firefox.exe'
            - 'outlook.exe'
    condition: selection_uri and selection_parent
falsepositives:
    - Legitimate developer clicking a trusted internal claude:// deep link
level: medium
```

**Known false positives:**

- Internal/trusted claude:// deep links used by developers for legitimate automation

**Tuning notes:** Scope the parent-process allowlist to your organization's approved browsers/mail clients and add a lookup of known-benign internal claude:// launchers to reduce noise; tighten the redirect join window if proxy logging lag is high.

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

- Hidden Below-the-Fold Prompt Payload Delivered via claude.ai/new?q= Parameter (Exploitation) (locked: unlock with TL Creds)
- Remote-Debug Code Insertion Into Project Source Files by MCP Filesystem-Server Process (Post-Exploitation) (locked: unlock with TL Creds)
- Conversation-History/Memory Search Followed by Local File Staging and Upload Attempt (C2/Exfiltration) (locked: unlock with TL Creds)
- claude.com Open-Redirect Used to Cloak claude:// or claude.ai/new Destination (Exploitation) (locked: unlock with TL Creds)
- Filesystem-Server MCP Process Writing Outside Its Approved Directory Scope (Post-Exploitation) (locked: unlock with TL Creds)
- Sandbox Egress to [indicator] Using a Non-Session API Key (C2/Credential Abuse) (locked: unlock with TL Creds)
- PowerShell/Shell Profile Write by AI-Agent or MCP Filesystem-Server Process (Post-Exploitation Persistence) (locked: unlock with TL Creds)
- Outbound Files-API Upload to [indicator] Immediately Following Untrusted URL Navigation (C2/Exfiltration) (locked: unlock with TL Creds)

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

## Sample indicators (1 of 16)

Defanged, TLP:CLEAR.

- Domain: `api[.]anthropic[.]com`

Full set of 16 indicators unlocks with TL Creds: https://threadlinqs.com/tl-creds

## Sources

- [Claude Flaw Automatically Sends Malicious Prompts to AI Agents](https://www.darkreading.com/vulnerabilities-threats/claude-flaw-malicious-prompts-ai-agents)
- [Claude.ai Vulnerability Analysis: Claudy Day (Oasis Security)](https://www.oasis.security/blog/claude-ai-prompt-injection-data-exfiltration-vulnerability)
- [Claude.ai Exploit Chain: Full Technical Report (Oasis Security)](https://www.oasis.security/resources/reports/claude-ai-prompt-injection-vulnerability-technical-report)
- [PromptFiction Flaw Auto-Submitted Hidden Prompts in Claude Desktop (Hackread)](https://hackread.com/promptfiction-flaw-auto-prompts-claude-desktop/)
- [Three high-risk AI vulnerabilities discovered in Claude.ai (TechRadar)](https://www.techradar.com/pro/security/three-high-risk-ai-vulnerabilities-discovered-in-claude-ai-end-to-end-attack-chain-exfiltrates-sensitive-info-without-user-knowing)
- [Anthropic Coordinated Vulnerability Disclosure Dashboard](https://red.anthropic.com/2026/cvd/)

## 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-2026-1380
