The Wire.AI Security News and Incident Tracker

Lead dispatch

First reported · updated · 2 reports bleepingcomputer.com

GitLab Patches Critical 9.9 AI Gateway Flaw Allowing Command Execution on Self-Hosted Servers

GitLab patched CVE-2026-90970, a critical (CVSS 9.9) flaw in its self-hosted AI Gateway service powering GitLab Duo features. An authenticated user with Duo Agent Platform access could escape the prompt template sandbox via a specially crafted flow configuration, leading to arbitrary command execution on the AI Gateway. Fixes shipped in versions 19.2.4, 19.3.2, and 19.4.1; GitLab-hosted instances are already protected.
Patched

sandbox-escape · remote-code-execution · prompt-injection · tool-abuse
ai-gateway · llm · gitlab-duo · ai-agents

Read the full dispatchQuery the index
Severity
0.82

The wire · latest

CLASS
AllThreatsNewsResearchAnalysisTools
TAGS
indirect-prompt-injectiontool-abusesupply-chaindata-exfiltration
More filters
TYPE
incidentresearchadvisoryanalysis
STATUS
In the wildPoCDisclosedPatched
Filteringthreat ×permission-bypass ×Clear all

First reported secmate.dev

Mistral Vibe Permission Bypass and Arbitrary Code Execution

SecMate disclosed two flaws in Mistral Vibe 2.25.0 (CVE-2026-87987 and CVE-2026-87984) where the coding agent's Bash tool used Tree-sitter to extract a reduced representation of a shell command for its permission allowlist, then executed the original untouched string. Hostile repository content could lead the model to emit a crafted tool call (e.g. an environment assignment prefixing an allowlisted command) that the permission parser classified as read-only, bypassing the approval prompt and enabling arbitrary code execution and reads/writes outside the authorized workspace. Mistral released Vibe 2.25.4 on September 12, 2026.
Patchedresearchpermission-bypassarbitrary-code-executioncommand-injectionindirect-prompt-injectiondata-exfiltrationtool-abuseai-agentscoding-agentllm
Details →
See the API docs to pull all 1337 items →

How the wire is made

Poll & cluster

Internet is crawled for AI security news and near-duplicate coverage is embedded and grouped into durable items.

Curate

AI Agent filters for agentic-AI relevance, classifies and tags each item, scores severity for threats, and writes the summary.

Read the full methodology →

Every item here is one machine-curated intelligence object, not a headline.

Agentic AI ThreatsAI Security ResearchAgentic AI Security ToolsPrompt InjectionTool Abuse

Read the wire for free. There is a small charge to ask the index questions.

The wire, open

The complete curated feed, no key required.

Subscribe to the RSS feed

The vector desk

Query the index by meaning, not just keyword.

  • GET /api/items?tags=&minSeverity=&itemType=
  • GET /api/search?q= — keyword
  • GET /api/semantic?q= — vector
Preview semantic search