First reported aithinkerlab.com
Lead dispatch
First reported · updated · 3 reports embracethered.com
AWS Kiro: Arbitrary Code Execution via Indirect Prompt Injection
Researchers found a vulnerability (CVE-2026-10591) in AWS Kiro, an agentic IDE, where hidden instructions planted in a web page or source file that Kiro processes can trigger indirect prompt injection to rewrite Kiro's own MCP server configuration (~/.kiro/settings/mcp.json) or allowlist arbitrary Bash commands in .vscode/settings.json, achieving arbitrary code execution on the developer's machine with no approval prompt. The human-in-the-loop approval boundary is bypassed because Kiro can write to these config files without user consent, and AWS has issued a fix and CVE.indirect-prompt-injection · prompt-injection · remote-code-execution · tool-abuse · config-poisoning
ai-agents · mcp · llm · agentic-ide
Severity
0.85
The wire · latest
First reported digicert.com
AI Deployment Outpaces AI Accountability
A commissioned DigiCert survey of 1,001 IT and security leaders reports that 78% of enterprises experienced AI-related security incidents or identified AI-related vulnerabilities, with incidents attributed largely to unauthorized or misconfigured AI agents rather than AI-generated code. The report frames the problem as a lack of AI governance and identity controls for non-human/agent actors, echoing a similar Spacelift finding. Details →First reported darkreading.com
AI-Generated Workflows Are a Silent Security Disaster
An opinion/commentary piece arguing that AI coding assistants used to generate Microsoft 365 automation (e.g., Power Automate workflows) create unreviewed permissions and data flows, citing an incident where an AI-generated workflow copied sensitive HR documents into a broadly accessible Teams channel. The piece frames this as a governance and oversight gap rather than presenting a specific reproducible exploit. Details →First reported skilldb.dev
Shipping an OAuth-protected remote MCP server: the spec, 3 security bugs, and a Cloud Run gotcha
An engineering blog post from SkillDB describing how they turned their MCP server into a remote, OAuth-protected MCP server for Claude Desktop, covering the MCP authorization spec (RFC 9728 protected resource metadata, 401 Bearer challenge), three OAuth security bugs caught in review before launch, and a Cloud Run infrastructure issue. Details →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.
Every item here is one machine-curated intelligence object, not a headline.
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.
- GET /feed.xml — RSS 2.0, every item
- GET /api/items — read-only
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