agenttriage-open-source

AgentTriage AgentTriage is a cross-agent tracing and security-diagnosis system for tool-using LLM agents. It observes source ingress, planning and tool lifecycles, normalizes them into one canonical event contract, reconstructs a Simplified Typed Provenance Graph STPG, extracts a source-to-sink...

An Exploration of Attacks on AI Agent Systems

As autonomous AI agents become more integrated into sensitive domains, it is crucial that single and multi-agent AI systems are secured. This paper investigates how prompt injection attacks can exploit both direct user inputs and inter?agent communication to leak sensitive information and trigger...

CVE-2026-63443 Coder: Workspace agent API insecure redirect handling allowed cross-agent file read and write

Coder allows organizations to provision remote development environments via Terraform. Prior to 2.29.19, 2.32.9, 2.33.10, and 2.34.4, agentConn.apiClient follows redirects while its custom transport accepts the host from the redirected request URL when the port is the workspace agent HTTP API por...

CVE-2026-63443 Coder: Workspace agent API insecure redirect handling allowed cross-agent file read and write

Coder allows organizations to provision remote development environments via Terraform. Prior to 2.29.19, 2.32.9, 2.33.10, and 2.34.4, agentConn.apiClient follows redirects while its custom transport accepts the host from the redirected request URL when the port is the workspace agent HTTP API por...

CVE-2026-63443 Coder: Workspace agent API insecure redirect handling allowed cross-agent file read and write

Coder allows organizations to provision remote development environments via Terraform. Prior to 2.29.19, 2.32.9, 2.33.10, and 2.34.4, agentConn.apiClient follows redirects while its custom transport accepts the host from the redirected request URL when the port is the workspace agent HTTP API por...

CVE-2026-84651

In Jenkins 2.579 and earlier, LTS 2.568.2 and earlier, the REST API and CLI endpoints for updating agent configuration do not prevent a submitted configuration from overwriting a different agent by specifying that agent's name in the submitted XML document, allowing attackers with Agent/Configure...

CVE-2026-84651

In Jenkins 2.579 and earlier, LTS 2.568.2 and earlier, the REST API and CLI endpoints for updating agent configuration do not prevent a submitted configuration from overwriting a different agent by specifying that agent's name in the submitted XML document, allowing attackers with Agent/Configure...

When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systems

Large language models are increasingly integrated into autonomous robotic systems for task planning and control, but this integration exposes them to prompt injection attacks that can lead to unsafe decisions and physical harm. Multi-agent settings increase the risks through cross-agent...

CVE-2026-57494

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/api prior to version 0.9.64, a low-privileged authenticated AgenticMail agent can enumerate another agent's pending/claimed tasks by supplying the target agent name to GET /api/agenticmail/tasks/pending?assignee=...

CVE-2026-57494

The CVE describes a cross‑agent task authorization bypass in AgenticMail. In @agenticmail/api versions before 0.9.64, a low‑privileged authenticated agent can enumerate another agent’s pending/claimed tasks via GET /api/agenticmail/tasks/pending?assignee=, receiving task IDs and payloads. Those I...

CVE-2026-57494

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/api prior to version 0.9.64, a low-privileged authenticated AgenticMail agent can enumerate another agent's pending/claimed tasks by supplying the target agent name to "GET /api/agenticmail/tasks/pending?assignee=...

CVE-2026-57494 AgenticMail: Cross-agent task authorization bypass in AgenticMail API

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/api prior to version 0.9.64, a low-privileged authenticated AgenticMail agent can enumerate another agent's pending/claimed tasks by supplying the target agent name to GET /api/agenticmail/tasks/pending?assignee=...

CVE-2026-57494 AgenticMail: Cross-agent task authorization bypass in AgenticMail API

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/api prior to version 0.9.64, a low-privileged authenticated AgenticMail agent can enumerate another agent's pending/claimed tasks by supplying the target agent name to GET /api/agenticmail/tasks/pending?assignee=...

CVE-2026-57494

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/api prior to version 0.9.64, a low-privileged authenticated AgenticMail agent can enumerate another agent's pending/claimed tasks by supplying the target agent name to GET /api/agenticmail/tasks/pending?assignee=...

EUVD-2026-46122

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/api prior to version 0.9.64, a low-privileged authenticated AgenticMail agent can enumerate another agent's pending/claimed tasks by supplying the target agent name to GET /api/agenticmail/tasks/pending?assignee=...

CVE-2026-57494 AgenticMail: Cross-agent task authorization bypass in AgenticMail API

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/api prior to version 0.9.64, a low-privileged authenticated AgenticMail agent can enumerate another agent's pending/claimed tasks by supplying the target agent name to GET /api/agenticmail/tasks/pending?assignee=...

CVE-2026-57494: Authorization Bypass Through User-Controlled Key

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/api prior to version 0.9.64, a low-privileged authenticated AgenticMail agent can enumerate another agent's pending/claimed tasks by supplying the target agent name to GET /api/agenticmail/tasks/pending?assignee=...

GO-2026-5923 Coder's workspace agent API insecure redirect handling allowed cross-agent file read and write in github.com/coder/coder

Coder's workspace agent API insecure redirect handling allowed cross-agent file read and write in github.com/coder/coder...

Coder's workspace agent API insecure redirect handling allowed cross-agent file read and write

Summary agentConn.apiClient used the default redirect behavior of http.Client while its custom transport dialed the host from the request URL as long as the port was the workspace agent HTTP API port 4. Agent tailnet IPs are deterministic from agent UUIDs, so a malicious workspace agent could...

GHSA-QRWJ-VH9X-GW5V Coder's workspace agent API insecure redirect handling allowed cross-agent file read and write

Summary agentConn.apiClient used the default redirect behavior of http.Client while its custom transport dialed the host from the request URL as long as the port was the workspace agent HTTP API port 4. Agent tailnet IPs are deterministic from agent UUIDs, so a malicious workspace agent could...