AgentCap: Capability-Based Runtime Authorization for Secure LLM Agent Execution

Language-model agents commonly collapse two decisions that security systems separate: selecting an action and determining whether that action is authorized. When a model exercises standing authority, indirect prompt injection can convert influence over its reasoning into unauthorized effects. We...

jataayu

🦅 Jataayu In the Ramayana, Jataayu was the eagle who spotted Ravana abducting Sita. He didn't wait for a pattern to match. He saw the threat, judged the situation, and acted — alone, without hesitation. That's Jataayu. The runtime authorization layer for tool-using AI agents. Gate the action, not...

Malicious code in cloud-runtime-authorization (npm)

The package cloud-runtime-authorization was found to contain malicious code. --- Credit: OpenSSF source...

The Vulnerability with No CVE: Managing Persistent Gaps between Mandate and Authority in AI Coding Agents

Existing guidance identifies excessive agency, excessive permission, weak task-bound authorization, and inadequate agent controls as important risks. Control frameworks also describe capabilities for constraining, authorizing, observing, validating, and responding to agent activity. Yet security...

ToolGuardian: Declarative Security for AI Agent-Tool Interactions

LLM agents increasingly rely on external tools, expanding capability while creating a new security boundary: third-party tools may appear benign at the interface level while embedding unsafe behavior in implementation. Existing defenses rely on weak metadata, collapse characterization and policy...

OpenClaw has a Discord `allowFrom` slug-collision authorization bypass

OpenClaw supports Discord allowlists using either user IDs or names/tags. Name/tag matching depends on slug normalization, so different user tags can collide to the same slug and unintentionally satisfy a name-based allowlist entry. Affected Packages / Versions - Package: openclaw npm - Affected...

Malicious code in cloud-runtime-authorization (npm)

The package cloud-runtime-authorization was found to contain malicious code...

MAL-2025-17169 Malicious code in cloud-runtime-authorization (npm)

The package cloud-runtime-authorization was found to contain malicious code...

CVE-2025-21620

Deno is a JavaScript, TypeScript, and WebAssembly runtime with secure defaults. When you send a request with the Authorization header to one domain, and the response asks to redirect to a different domain, Deno'sfetch redirect handling creates a follow-up redirect request that keeps the original...