Lucene search
+L

4712 matches found

OSV
OSV
added 2026/06/18 2:32 p.m.7 views

CVE-2026-22551

In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP requests to arbitrary external URLs without restriction. Combined with prompt injection in a malicious workspace, an attacker could induce the AI agent to construct image URLs...

6.7CVSS6AI score
SaveExploits0References4
CVE
CVE
added 2026/06/18 2:32 p.m.30 views

CVE-2026-22551

Eclipse Theia versions before 1.71.0 are affected: the AI chat could render Markdown image tags from AI responses, causing HTTP requests to arbitrary external URLs. In combination with a malicious workspace via prompt injection, an attacker could coax the AI agent to construct image URLs that lea...

6.7CVSS5.5AI score0.00312EPSS
SaveExploits0References1Affected Software1
ATTACKERKB
ATTACKERKB
added 2026/06/18 2:32 p.m.8 views

CVE-2026-22551

In Eclipse Theia versions prior to 1.71.0, the AI chat rendered Markdown image tags from AI responses, triggering HTTP requests to arbitrary external URLs without restriction. Combined with prompt injection in a malicious workspace, an attacker could induce the AI agent to construct image URLs...

6.7CVSS5.4AI score0.00312EPSS
SaveExploits0References2
Github Security Blog
Github Security Blog
added 2026/06/18 2:27 p.m.15 views

PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation

Summary The multiedit tool in src/praisonai/praisonai/tools/multiedit.py allows LLM-controlled arbitrary file read and write without any path validation, workspace boundary check, or protected path guard. This enables an attacker who can influence agent tool arguments via crafted prompts, user...

5.8AI score
SaveExploits0References2Affected Software1
OSV
OSV
added 2026/06/18 2:27 p.m.10 views

GHSA-29W3-P9W9-WC47 PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation

Summary The multiedit tool in src/praisonai/praisonai/tools/multiedit.py allows LLM-controlled arbitrary file read and write without any path validation, workspace boundary check, or protected path guard. This enables an attacker who can influence agent tool arguments via crafted prompts, user...

9.1CVSS5.9AI score
SaveExploits0References2
CVE
CVE
added 2026/06/18 2:26 p.m.44 views

CVE-2026-46580

Theia before v1.71.0 loads files matching .prompts/*.prompttemplate from a workspace, allowing attacker-controlled content to override the AI agent’s system prompts (indirect prompt injection). This enables attack chains with untrusted workspaces, potentially causing data exfiltration via Markdow...

8.8CVSS5.7AI score0.00507EPSS
SaveExploits0References1Affected Software1
OSV
OSV
added 2026/06/18 2:26 p.m.7 views

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...

8.4CVSS6.2AI score
SaveExploits0References4
ATTACKERKB
ATTACKERKB
added 2026/06/18 2:26 p.m.7 views

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...

8.4CVSS5.6AI score0.00507EPSS
SaveExploits0References2
EUVD
EUVD
added 2026/06/18 2:22 p.m.16 views

EUVD-2026-37898

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...

8.4CVSS5.7AI score0.00507EPSS
SaveExploits0References1
Cvelist
Cvelist
added 2026/06/18 2:22 p.m.30 views

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...

8.4CVSS0.00507EPSS
SaveExploits0References1
Snyk
Snyk
added 2026/06/18 1:59 p.m.12 views

Incorrect Authorization

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

8.5CVSS5.8AI score
SaveExploits0References3
Github Security Blog
Github Security Blog
added 2026/06/18 1:59 p.m.16 views

PraisonAI Code agent tools fail open without a workspace boundary

PraisonAI Code agent tools fail open without a workspace boundary Summary PraisonAI Code's agent-compatible CODETOOLS wrappers keep a global workspace root initialized to None. If an application uses CODETOOLS, codereadfile, codesearchreplace, or codeapplydiff before calling setworkspace, the...

5.6AI score
SaveExploits0References2Affected Software1
OSV
OSV
added 2026/06/18 1:59 p.m.7 views

GHSA-GCQ3-MFVH-3X25 PraisonAI Code agent tools fail open without a workspace boundary

PraisonAI Code agent tools fail open without a workspace boundary Summary PraisonAI Code's agent-compatible CODETOOLS wrappers keep a global workspace root initialized to None. If an application uses CODETOOLS, codereadfile, codesearchreplace, or codeapplydiff before calling setworkspace, the...

7.3CVSS5.6AI score
SaveExploits0References2
Github Security Blog
Github Security Blog
added 2026/06/18 1:58 p.m.15 views

PraisonAI: Missing ownership check on DELETE endpoints allows members to delete others' content in Platform API

Summary A workspace member can permanently delete any resource — projects, agents, issues, labels, issue dependencies, and issue-label attachments — created by the workspace owner or other members. All six content DELETE endpoints enforce workspace membership but perform no ownership or role chec...

5.4AI score
SaveExploits0References2Affected Software1
OSV
OSV
added 2026/06/18 1:58 p.m.10 views

GHSA-RH39-9C67-59MH PraisonAI: Missing ownership check on DELETE endpoints allows members to delete others' content in Platform API

Summary A workspace member can permanently delete any resource — projects, agents, issues, labels, issue dependencies, and issue-label attachments — created by the workspace owner or other members. All six content DELETE endpoints enforce workspace membership but perform no ownership or role chec...

8.1CVSS5.4AI score
SaveExploits0References2
Snyk
Snyk
added 2026/06/18 1:58 p.m.9 views

Improper Authorization

Overview praisonai-platform is a Platform layer for PraisonAI — workspace, auth, issues, projects Affected versions of this package are vulnerable to Improper Authorization in the DELETE process for workspace resources. An attacker can irreversibly remove content belonging to other users by sendi...

8.1CVSS5.8AI score
SaveExploits0References2
Github Security Blog
Github Security Blog
added 2026/06/18 1:57 p.m.16 views

PraisonAI: Arbitrary File Read via `@file:` Mention Path Traversal

Summary The MentionsParser in src/praisonai-agents/praisonaiagents/tools/mentions.py processes @file: mentions in agent prompts by reading arbitrary files from the filesystem. When a file path is not found relative to the workspace, the parser falls back to using the path as an absolute path...

5.6AI score
SaveExploits0References2Affected Software1
OSV
OSV
added 2026/06/18 1:57 p.m.8 views

GHSA-2RCG-MM5H-XCHX PraisonAI: Arbitrary File Read via `@file:` Mention Path Traversal

Summary The MentionsParser in src/praisonai-agents/praisonaiagents/tools/mentions.py processes @file: mentions in agent prompts by reading arbitrary files from the filesystem. When a file path is not found relative to the workspace, the parser falls back to using the path as an absolute path...

7.5CVSS5.7AI score
SaveExploits0References2
OSV
OSV
added 2026/06/18 1:4 p.m.9 views

GHSA-FQ9J-VW4W-FR6V OpenClaw: Workspace .env CLOUDSDK_PYTHON could influence Gmail setup gcloud execution

Summary Workspace .env CLOUDSDKPYTHON could influence Gmail setup gcloud execution. In affected versions, a workspace .env in a repository opened by a trusted operator could influence which Python runtime gcloud used through CLOUDSDKPYTHON. This advisory is scoped to the named feature and...

7.1CVSS5.7AI score0.00133EPSS
SaveExploits0References4
Positive Technologies
Positive Technologies
added 2026/06/18 12:0 a.m.27 views

PT-2026-50688

Name of the Vulnerable Software and Affected Versions Eclipse Theia versions prior to 1.71.0 Description The AI chat renders Markdown image tags from AI responses, which triggers unrestricted HTTP requests to arbitrary external URLs. When combined with prompt injection in a malicious workspace, a...

6.7CVSS6AI score0.00312EPSS
SaveExploits0References10
Rows per page
Query Builder