GHSA-M973-PR9R-HP2W [Eclipse Theia] Indirect Prompt Injection via Auto-Loaded Workspace Prompt Template Files in AI Chat

In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the...

[Eclipse Theia] Indirect Prompt Injection via Adversarial Workspace File and Directory Names in AI Chat

In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacker could craft a malicious repository with adversarial directory or file names that, when analyzed...

CVE-2026-44688

In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacker could craft a malicious repository with adversarial directory or file names that, when analyzed...

EUVD-2026-37899

In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the...

CVE-2026-46580

In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the...

CVE-2026-44688

In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacker could craft a malicious repository with adversarial directory or file names that, when analyzed...

CVE-2026-44688

In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacker could craft a malicious repository with adversarial directory or file names that, when analyzed...

PT-2026-50691

Name of the Vulnerable Software and Affected Versions Eclipse Theia versions prior to 1.71.0 Description Files matching the pattern .prompts/.prompttemplate in a workspace are automatically loaded, allowing them to override or extend the AI agent's system prompts. This enables indirect prompt...

PT-2026-50689

Name of the Vulnerable Software and Affected Versions Eclipse Theia versions prior to 1.71.0 Description The AI chat agent processes workspace file and directory names as part of its prompt context without distinguishing them from system instructions. This allows for indirect prompt injection,...

CVE-2026-3490

picklescan before 1.0.4 fails to block pkgutil.resolvename, allowing attackers to bypass the entire blocklist by resolving any dangerous function through indirect REDUCE calls. Remote attackers can invoke any blocked function such as os.system, builtins.exec, or subprocess.call to achieve remote...

CVE-2026-3490

CVE-2026-3490 affects picklescan prior to version 1.0.4, where the blocklist of dangerous functions is bypassed via pkgutil.resolve_name. The underlying issue is an incomplete blocklist that allows indirect REDUCE calls to resolve dangerous functions, enabling remote code execution (e.g., os.syst...

Hiding in Plain Floats: Steganographic Carriers for Indirect Prompt and Content Injection

Text-centered prompt-injection defenses assume that the malicious signal is visible in one of the inspected text views. We study a reproducible LLM01-style indirect prompt/content-injection failure mode where that assumption breaks: a payload caught in plain English slips past the same detector...

CVE-2026-39966

TypeBot is a chatbot builder tool. In versions 3.15.2, the getLinkedTypebots API endpoint returns full bot definitions to any authenticated user who references a target bot ID in a Typebot Link block, regardless of workspace ownership, leading to IDOR. The authorization check uses Array.filter wi...

CVE-2026-4503

IBM Langflow Desktop 1.0.0 through 1.8.4 Langflow could allow an unauthenticated user to view other users' images due to an indirect object reference through a user-controlled key...

CVE-2026-11369

The Comment API GET /api/Comment and POST /api/Comment in the affected application fails to perform authorization checks to verify that the requesting user has access to the object identified by the relatedObjectId. This Insecure Direct Object Reference IDOR vulnerability allows any authenticated...

CVE-2026-24756 Kiteworks Secure Data Forms is vulnerable to Authorization Bypass Through User-Controlled Key

Kiteworks is a private data network PDN. Prior to version 9.3.0, an Insecure Direct Object Reference IDOR vulnerability in Kiteworks Secure Data Forms allows an authenticated user to modify resources belonging to other users due to insufficient authorization checks on resource ownership. Upgrade...

CVE-2026-24755

Kiteworks is a private data network PDN. Prior to version 9.3.0, an Insecure Direct Object Reference IDOR vulnerability in Kiteworks Secure Data Forms allows an authenticated user to modify permissions on resources belonging to other users due to insufficient authorization checks on resource...

AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations

Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations third-party services such as Gmail, Salesforce, or Jira accessed through tool calls whose response content the user neither writes nor controls. Existing benchmarks under-measure the...

SUSE CVE-2026-46218

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Add bounds checking to ibget,setvalue The uvd/vce/vcn code accesses the IB at predefined offsets without checking that the IB is large enough. Check the bounds here. The caller is responsible for making sure it can...

CVE-2026-46218 drm/amdgpu: Add bounds checking to ib_{get,set}_value

In the Linux kernel, the following vulnerability has been resolved: drm/amdgpu: Add bounds checking to ibget,setvalue The uvd/vce/vcn code accesses the IB at predefined offsets without checking that the IB is large enough. Check the bounds here. The caller is responsible for making sure it can...